© 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. 95220
    Prev
    Next
    INDEX
    Explanations

    analytics

    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
    migrationBuilder
    -0.68
    PyExc
    -0.66
     ModelExpression
    -0.63
     Analytics
    -0.62
    fram
    -0.61
     analytics
    -0.60
     Rus
    -0.59
     salts
    -0.59
     dies
    -0.58
    entiary
    -0.57
    POSITIVE LOGITS
    HandlerContext
    0.58
     mãos
    0.54
     sred
    0.54
     gyakor
    0.54
     excepted
    0.51
     vastaan
    0.49
    Susie
    0.49
    ėms
    0.49
     Doreen
    0.48
    roveň
    0.48
    Activations Density 0.339%

    No Known Activations