© 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. 90842
    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
    <bos>
    -1.19
    parsedMessage
    -1.01
    
    -0.89
    ViewFeatures
    -0.88
    enumi
    -0.82
     autorytatywna
    -0.82
    MigrationBuilder
    -0.80
    webElementXpaths
    -0.79
    InSection
    -0.79
     Савезне
    -0.77
    POSITIVE LOGITS
     by
    0.56
     don
    0.55
     or
    0.55
     has
    0.54
     had
    0.54
     have
    0.54
     at
    0.52
     is
    0.52
     m
    0.52
     are
    0.52
    Activations Density 0.332%

    No Known Activations