© 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. 78205
    Prev
    Next
    INDEX
    Explanations

    log/sign

    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
     Italijanski
    -0.75
    djangoproject
    -0.70
     MainAxisSize
    -0.65
    InvalidProtocol
    -0.63
    andExpect
    -0.60
     NDEBUG
    -0.59
    IsMutable
    -0.56
    CppCodeGen
    -0.54
    UnusedPrivate
    -0.54
    GEBURTSDATUM
    -0.52
    POSITIVE LOGITS
     out
    0.97
     off
    0.90
     on
    0.75
     over
    0.71
    out
    0.69
     into
    0.63
     down
    0.62
     Out
    0.59
     up
    0.57
     onto
    0.56
    Activations Density 0.005%

    No Known Activations