© 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. 4-CLT-HP
    7. 219
    Prev
    Next
    INDEX
    Explanations

    country

    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
    (_,
    -0.56
    ⁎
    -0.56
    idenav
    -0.54
    quillas
    -0.54
    Zobacz
    -0.54
     offences
    -0.52
     shortage
    -0.52
    %"
    -0.51
     assiste
    -0.51
     tongues
    -0.50
    POSITIVE LOGITS
    GEBURTSDATUM
    0.54
    reportWebVitals
    0.52
    featureID
    0.48
    toHexString
    0.48
     world
    0.47
    .
    0.47
     مواليد
    0.46
    ագրություններ
    0.46
    SaveChangesAsync
    0.45
    migrationBuilder
    0.45
    Activations Density 0.004%

    No Known Activations