© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96548
    Prev
    Next
    INDEX
    Explanations

    using

    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
    捌
    -0.51
    absor
    -0.48
    EmptyString
    -0.48
     sinc
    -0.46
    Ever
    -0.45
    scalatest
    -0.45
    abela
    -0.45
    wußt
    -0.45
    Revenir
    -0.45
    versus
    -0.45
    POSITIVE LOGITS
     nahilalakip
    0.82
     defaultstate
    0.81
    Бахар
    0.74
    TintMode
    0.73
    HideFlags
    0.72
    InjectAttribute
    0.72
    interopRequire
    0.71
    TagMode
    0.68
    MigrationBuilder
    0.67
    حياتها
    0.66
    Activations Density 0.009%

    No Known Activations