© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9738
    Prev
    Next
    INDEX
    Explanations

    law enforcement

    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
    AndEndTag
    -0.70
     GoogleFonts
    -0.67
    <bos>
    -0.67
    VIAF
    -0.63
     StatefulWidget
    -0.59
    aarrggbb
    -0.56
     dovuto
    -0.56
     StatelessWidget
    -0.55
    ParallelGroup
    -0.54
    styleable
    -0.54
    POSITIVE LOGITS
     ویکی‌پدیا
    0.56
    IntoConstraints
    0.55
    StructEnd
    0.49
    scriptcase
    0.48
     verfü
    0.47
    género
    0.46
    fatalError
    0.46
     gainera
    0.46
    Տես
    0.45
     sqlalchemy
    0.42
    Activations Density 0.049%

    No Known Activations