© 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. 73050
    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
     out
    -0.39
     in
    -0.39
     over
    -0.36
     on
    -0.34
    ..
    -0.34
    EntityFramework
    -0.32
     up
    -0.31
    衅
    -0.31
     off
    -0.31
     en
    -0.30
    POSITIVE LOGITS
     ſche
    0.77
     Theſe
    0.73
     purpoſe
    0.73
    MigrationBuilder
    0.67
     ſmall
    0.66
     ſtate
    0.66
     pleaſure
    0.66
     houſe
    0.65
    NewUrlParser
    0.65
    ’”
    0.65
    Activations Density 0.001%

    No Known Activations