© 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. 8964
    Prev
    Next
    INDEX
    Explanations

    script

    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
     script
    -1.46
     scripts
    -1.21
     Script
    -1.14
    Script
    -1.09
    script
    -0.95
     Scripts
    -0.94
    脚本
    -0.93
     SCRIPT
    -0.83
    SCRIPT
    -0.74
     scripting
    -0.73
    POSITIVE LOGITS
    ագրություններ
    0.88
     Audiodateien
    0.76
     eorum
    0.73
    LEncoder
    0.72
     correctes
    0.71
    InjectAttribute
    0.71
     phénom
    0.70
    IntoConstraints
    0.70
     épar
    0.68
     épis
    0.68
    Activations Density 0.210%

    No Known Activations