© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41231
    Prev
    Next
    INDEX
    Explanations

    way

    np_max-act · 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
    ↵↵
    -0.90
    a
    -0.81
     
    -0.77
    ↵
    -0.76
     in
    -0.76
     of
    -0.74
     a
    -0.73
    .
    -0.70
     the
    -0.69
     (
    -0.68
    POSITIVE LOGITS
    AndEndTag
    1.52
     ―――――
    1.33
    NUMX
    1.31
     Efq
    1.30
    ]")]
    1.23
    httphttps
    1.23
     Мексичка
    1.21
    ^(@)
    1.19
     ་་
    1.16
    ThroughAttribute
    1.16
    Activations Density 0.074%

    No Known Activations