© 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. 94274
    Prev
    Next
    INDEX
    Explanations

    Media/Installments

    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
    gat
    -0.85
     instalment
    -0.61
    Karakteristik
    -0.59
     Balboa
    -0.56
     aDecoder
    -0.55
    Portail
    -0.54
     installment
    -0.52
    RectangleBorder
    -0.50
    ipedi
    -0.49
     collateral
    -0.46
    POSITIVE LOGITS
    InjectAttribute
    0.67
    InitVars
    0.63
    AndEndTag
    0.61
     متحده
    0.52
    hésite
    0.52
    IsContent
    0.50
     Hidup
    0.49
    zędu
    0.49
    toHaveBeen
    0.48
    jsxFileName
    0.48
    Activations Density 0.086%

    No Known Activations