© 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. 1-CLT-HP
    7. 9795
    Prev
    Next
    INDEX
    Explanations

    authentic

    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
    <bos>
    -0.85
    __':
    -0.80
    __':
    -0.73
    boten
    -0.59
     and
    -0.57
    verwijspagina
    -0.56
    addPreferredGap
    -0.56
    úgó
    -0.56
     Her
    -0.54
    SerializedName
    -0.54
    POSITIVE LOGITS
    tvguidetime
    0.80
    ulipas
    0.58
    zeß
    0.56
    ListItemIcon
    0.53
     artifacts
    0.53
     ModelExpression
    0.52
     configureStore
    0.52
    ++
    0.51
     كومونز
    0.51
    IsContent
    0.50
    Activations Density 0.009%

    No Known Activations