© 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. 20-CLT-HP
    7. 71269
    Prev
    Next
    INDEX
    Explanations

    Code related

    np_max-act-logits · 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
    UnsafeEnabled
    -0.79
    AutoScaleMode
    -0.77
    ThroughAttribute
    -0.75
    medriver
    -0.72
    ImageContext
    -0.70
     RoutedEventArgs
    -0.70
    Tikang
    -0.70
     nahilalakip
    -0.69
     Stretcher
    -0.69
    ErrUnexpectedEOF
    -0.68
    POSITIVE LOGITS
    Post
    0.50
    Host
    0.46
    Embed
    0.45
    Import
    0.45
     Sync
    0.43
    Sync
    0.42
    post
    0.42
     Host
    0.41
     post
    0.40
    )}+
    0.40
    Activations Density 0.001%

    No Known Activations