© 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. 78001
    Prev
    Next
    INDEX
    Explanations

    by

    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
    '}),
    -0.70
     estekak
    -0.63
    parsedMessage
    -0.62
    contentLoaded
    -0.61
    InjectAttribute
    -0.60
    ConstraintMaker
    -0.57
    ])[
    -0.57
    Lähteet
    -0.57
    astify
    -0.56
    tagext
    -0.56
    POSITIVE LOGITS
    rights
    0.63
     federal
    0.61
     far
    0.59
    federal
    0.58
     official
    0.58
     Congressional
    0.58
     executive
    0.57
     droits
    0.57
     rights
    0.56
     presidential
    0.56
    Activations Density 0.003%

    No Known Activations