© 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. 0-CLT-HP
    7. 42902
    Prev
    Next
    INDEX
    Explanations

    medical issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trade
    -1.90
     Trade
    -1.42
    Trade
    -1.28
    trade
    -1.28
     TRADE
    -1.19
    TRADE
    -1.00
     abdominal
    -0.88
     trades
    -0.82
     trading
    -0.77
    贸易
    -0.71
    POSITIVE LOGITS
     ―――――
    1.18
     itſelf
    1.15
     myſelf
    1.12
     doubtnut
    1.10
     auffi
    1.06
     ་་
    1.06
     يتيمه
    1.05
    GraphicsUnit
    1.03
     متعلقه
    1.02
    oa̍t
    1.02
    Activations Density 0.608%

    No Known Activations