© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8995
    Prev
    Next
    INDEX
    Explanations

    area

    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
    ValueStyle
    -0.54
    BackStack
    -0.49
    ScopeManager
    -0.48
    QName
    -0.46
    RectF
    -0.43
    ContentLoaded
    -0.42
    日閲覧
    -0.41
     graphql
    -0.40
     Hentet
    -0.40
    newblock
    -0.40
    POSITIVE LOGITS
    はじめに
    0.72
     NUKAT
    0.67
     dAtA
    0.63
     وتسجيلات
    0.61
     متعلقه
    0.61
     CreateTagHelper
    0.61
     BNE
    0.61
    insee
    0.59
    حياته
    0.57
    Tikang
    0.57
    Activations Density 0.017%

    No Known Activations