© 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. 77948
    Prev
    Next
    INDEX
    Explanations

    Computer code and graphs

    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
    Not in Any Lists

    No Comments

    Negative Logits
     GG
    -0.96
     GSC
    -0.94
     GJ
    -0.94
    enumi
    -0.93
     GK
    -0.93
     GD
    -0.92
     للاسماء
    -0.92
     GV
    -0.92
    GZIP
    -0.91
     JG
    -0.91
    POSITIVE LOGITS
    Of
    0.47
    S
    0.44
    ха
    0.43
    ith
    0.43
    L
    0.42
    M
    0.42
    R
    0.42
     Se
    0.41
    ir
    0.41
    The
    0.40
    Activations Density 0.004%

    No Known Activations