© 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. 71411
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    
    -0.60
     ―――――
    -0.59
    hazi
    -0.58
    DropTable
    -0.57
    contentLoaded
    -0.56
     فريبيس
    -0.55
    amond
    -0.54
    帖最后由
    -0.53
    DropColumn
    -0.52
     raiſ
    -0.52
    POSITIVE LOGITS
    الإنجليزية
    0.57
    fjspx
    0.57
    HideFlags
    0.54
    eraan
    0.51
    thansa
    0.51
    queryInterface
    0.49
     оригіналу
    0.48
     imageNamed
    0.48
    webElementXpaths
    0.48
    parsedMessage
    0.48
    Activations Density 0.002%

    No Known Activations