© 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. 10497
    Prev
    Next
    INDEX
    Explanations

    survey

    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
     survey
    -0.80
    survey
    -0.71
     Survey
    -0.71
     SURVEY
    -0.70
    Survey
    -0.69
     Surveys
    -0.68
     surveys
    -0.56
    Surveys
    -0.54
     surveying
    -0.53
     surveyed
    -0.52
    POSITIVE LOGITS
     ModelExpression
    0.85
     незавершена
    0.78
     تضيفلها
    0.67
    NameInMap
    0.66
    OGND
    0.65
    RegistryLite
    0.65
    TestingModule
    0.63
    sizeCache
    0.63
     transférez
    0.63
     disambiguazione
    0.61
    Activations Density 0.025%

    No Known Activations