© 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. 9276
    Prev
    Next
    INDEX
    Explanations

    school

    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
    GEBURTSDATUM
    -0.82
     للمعارف
    -0.77
     AssemblyTitle
    -0.76
    featureID
    -0.75
     ModelExpression
    -0.68
    UserScript
    -0.68
     <>",
    -0.67
     Seeder
    -0.66
     Biôgrafia
    -0.65
    mybatisplus
    -0.65
    POSITIVE LOGITS
    AsyncResult
    0.56
     cascades
    0.45
     recital
    0.44
     symphon
    0.42
     conv
    0.42
     ministry
    0.42
     MIME
    0.42
    外部リンク
    0.42
     kask
    0.41
     Knoxville
    0.41
    Activations Density 0.038%

    No Known Activations