© 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. 95483
    Prev
    Next
    INDEX
    Explanations

    immediately

    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
     drop
    -1.45
     Drop
    -1.41
     dropped
    -1.37
     immediately
    -1.34
     dropping
    -1.30
    Drop
    -1.24
    dropping
    -1.20
    immediately
    -1.17
    drop
    -1.14
     DROP
    -1.13
    POSITIVE LOGITS
     scolaires
    0.68
     متعلقه
    0.63
     zove
    0.58
     sogget
    0.57
     judiciaire
    0.54
     nodeId
    0.54
     scolaire
    0.53
     fréquence
    0.52
     aisladas
    0.52
    anskje
    0.52
    Activations Density 0.059%

    No Known Activations