© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1615
    Prev
    Next
    INDEX
    Explanations

    medical terms, especially in the context of imaging results and patient descriptions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाओं
    -0.74
     createSprite
    -0.56
    ValueStyle
    -0.54
    Koordinaten
    -0.52
    出版年
    -0.52
     /\.(
    -0.50
    锈钢
    -0.49
    dicionado
    -0.48
     mouth
    -0.48
    keleton
    -0.48
    POSITIVE LOGITS
     Boch
    0.57
     masses
    0.54
    masse
    0.53
    compress
    0.53
     bilo
    0.53
     mass
    0.52
     Dube
    0.52
     sell
    0.52
     tumor
    0.52
     abscess
    0.51
    Activations Density 0.835%

    No Known Activations