© 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. 94771
    Prev
    Next
    INDEX
    Explanations

    Crafted/Sudden

    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
    zulegen
    -0.66
    ConstraintMaker
    -0.66
    zunehmen
    -0.56
    née
    -0.54
    cised
    -0.50
    ума
    -0.49
    ising
    -0.48
     ويكيپيديا
    -0.48
    ,‎
    -0.47
    országban
    -0.47
    POSITIVE LOGITS
    참고
    0.85
    ंदीखरीदारी
    0.76
    istoitu
    0.70
    AccessorTable
    0.68
     ProtoMessage
    0.66
    GraphicsUnit
    0.66
     Democrá
    0.63
     مشين
    0.63
     TextInputType
    0.62
    WithIOException
    0.61
    Activations Density 0.082%

    No Known Activations