© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73172
    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
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.92
     betweenstory
    -0.79
    ViewFeatures
    -0.77
     виправивши
    -0.75
    :✨
    -0.70
    CloseOperation
    -0.70
    Personensuche
    -0.67
    ScopeManager
    -0.66
    EndInit
    -0.65
     contextLoads
    -0.65
    POSITIVE LOGITS
     drove
    0.56
     drive
    0.55
     drives
    0.50
     rode
    0.48
     driven
    0.47
    drive
    0.47
     select
    0.46
     lived
    0.45
     Drive
    0.44
    drives
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.