© 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. 5-CLT-HP
    7. 91011
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ViewFeatures
    -0.73
     AssemblyCulture
    -0.69
    WillAppear
    -0.69
     HttpNotFound
    -0.69
    RetentionPolicy
    -0.67
     ComVisible
    -0.64
    mybatisplus
    -0.64
    GEBURTSDATUM
    -0.63
    Hochspringen
    -0.63
    Abitanti
    -0.62
    POSITIVE LOGITS
    RegistryLite
    0.56
     кӀ
    0.53
    mis
    0.46
    sizeCache
    0.46
    ones
    0.45
    Free
    0.45
    льников
    0.44
    s
    0.44
    новништво
    0.44
     of
    0.43
    Activations Density 0.004%

    No Known Activations