© 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. 5-CLT-HP
    7. 6309
    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
     Efq
    -0.70
     ſeveral
    -0.62
     Majefty
    -0.62
     pleaſure
    -0.61
     raiſ
    -0.60
     whoſe
    -0.59
     itſelf
    -0.58
     Diſ
    -0.56
     themſelves
    -0.56
     becauſe
    -0.56
    POSITIVE LOGITS
     للاسماء
    0.72
     ProtoMessage
    0.66
    aarrggbb
    0.63
     surla
    0.63
    MigrationBuilder
    0.60
    AddTagHelper
    0.58
     brings
    0.56
     thinks
    0.55
    Espèce
    0.54
     think
    0.50
    Activations Density 0.004%

    No Known Activations