© 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. 78179
    Prev
    Next
    INDEX
    Explanations

    technical text

    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
     الرياضيه
    -0.57
    MessageTagHelper
    -0.55
    enderror
    -0.54
    ähle
    -0.51
    veloppement
    -0.49
     deportiva
    -0.48
     änd
    -0.48
     Impressions
    -0.46
    $__
    -0.46
    ffiche
    -0.45
    POSITIVE LOGITS
    مصادر
    0.62
    MeasureSpec
    0.61
    GraphicsUnit
    0.59
    pinMode
    0.57
     MessageBoxIcon
    0.56
    mybatisplus
    0.56
     betweenstory
    0.52
    InSection
    0.52
     riot
    0.52
    клопе
    0.52
    Activations Density 0.001%

    No Known Activations