© 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. 0-CLT-HP
    7. 95017
    Prev
    Next
    INDEX
    Explanations

    mind

    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
    a
    -0.52
    CreateMap
    -0.52
     INTERESAR
    -0.44
     tissue
    -0.43
    UpInside
    -0.42
    做一个
    -0.42
     kontaktieren
    -0.41
    udesta
    -0.41
     of
    -0.41
    úcar
    -0.40
    POSITIVE LOGITS
     propOrder
    0.90
    CodedInputStream
    0.81
     الحره
    0.76
    hésite
    0.74
    Numerology
    0.73
    windowFixed
    0.73
    RegressionTest
    0.72
    Personensuche
    0.71
    épaisseur
    0.69
    WindowConstants
    0.69
    Activations Density 2.178%

    No Known Activations