© 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. 5-CLT-HP
    7. 5666
    Prev
    Next
    INDEX
    Explanations

    groups of people/entities

    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
    <bos>
    -0.61
    CodeAttribute
    -0.52
    ArgsConstructor
    -0.50
     learned
    -0.49
     audiences
    -0.49
    のお客様
    -0.48
     aman
    -0.47
    oples
    -0.47
    bbean
    -0.47
    цвет
    -0.47
    POSITIVE LOGITS
    WebElementEntity
    0.71
    évaluateur
    0.66
     HasFactory
    0.64
    Externí
    0.56
     Réponses
    0.55
    antMatchers
    0.55
     Infórmanos
    0.54
     الحره
    0.54
    protoimpl
    0.53
    …~
    0.53
    Activations Density 0.001%

    No Known Activations