Vector Embedding Similarity Visualization MicroSim
Run the Vector Embedding Similarity Visualization MicroSim MicroSim Fullscreen
About This MicroSim
This MicroSim shows how medical concepts are arranged in a vector embedding space so that semantically similar concepts sit close together, and how similarity search retrieves the nearest concepts to a query. Twenty conditions are projected into two dimensions and colored by category — cardiovascular, respiratory, neurological, and metabolic. A clinical query is placed in the space, and lines connect it to its most similar concepts, with cosine-similarity scores in the results panel.
How to Use
Choose a clinical query from the dropdown — "Chest pain and dyspnea," for instance, lands between the cardiovascular and respiratory clusters and matches concepts from both. Adjust the Neighbors slider to return more or fewer matches and the Threshold slider to require a minimum similarity (the dashed circle shows that boundary). The results panel lists each matched concept with its similarity percentage.
Iframe Embed Code
You can add this MicroSim to any web page by adding this to your HTML:
1 2 3 4 | |
Lesson Plan
Grade Level
9-12 (High School Geometry)
Duration
10-15 minutes
Prerequisites
TODO: List prerequisites.
Activities
- Exploration (5 min): TODO
- Guided Practice (5 min): TODO
- Assessment (5 min): TODO
Assessment
TODO: List assessment criteria.
References
- TODO: Add references.