© 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. 0-CLT-HP
    7. 95782
    Prev
    Next
    INDEX
    Explanations

    Code/special characters

    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
    Negative Logits
    แ
    -0.49
    amentul
    -0.45
    idex
    -0.44
     grava
    -0.43
    ведении
    -0.40
    بية
    -0.40
     schi
    -0.39
    hy
    -0.39
    chy
    -0.39
    ಗ
    -0.38
    POSITIVE LOGITS
     AssemblyCulture
    0.98
     ExecuteAsync
    0.95
    AndEndTag
    0.91
    ReusableCell
    0.86
    TypedDataSet
    0.85
    bootstrapcdn
    0.83
    ViewImports
    0.80
    RenderAtEndOf
    0.80
    GEBURTSDATUM
    0.79
     itſelf
    0.79
    Activations Density 0.006%

    No Known Activations