© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 728
    Prev
    Next
    INDEX
    Explanations

    mentions of CD9 and CD10 in medical texts

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Elen
    -0.65
    Teng
    -0.60
    >');
    -0.59
    erti
    -0.59
     Vaz
    -0.58
     elena
    -0.58
     Ass
    -0.57
    ItemLayout
    -0.56
     Eccl
    -0.56
    UpdateCommand
    -0.55
    POSITIVE LOGITS
     CD
    2.80
    CD
    2.50
     cd
    2.09
     CDs
    2.05
    CDs
    1.75
    cd
    1.64
    Cd
    1.46
     cds
    1.45
     DVD
    1.38
     Cd
    1.37
    Activations Density 0.213%

    No Known Activations