© 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. 9157
    Prev
    Next
    INDEX
    Explanations

    balance

    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
    D
    -0.51
    dens
    -0.47
    ыл
    -0.44
    agrama
    -0.44
     ویکی‌پدیای
    -0.44
     مهد
    -0.43
    Failing
    -0.42
    лица
    -0.42
    cas
    -0.42
    attendre
    -0.42
    POSITIVE LOGITS
    ItemGroup
    0.71
     IBOutlet
    0.66
    Tikang
    0.65
    fromnode
    0.64
    ioutil
    0.63
    IntoConstraints
    0.62
    enumii
    0.60
     onOptions
    0.58
    ModelAdmin
    0.58
     ModelExpression
    0.58
    Activations Density 0.004%

    No Known Activations