© 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. 1-CLT-HP
    7. 8743
    Prev
    Next
    INDEX
    Explanations

    supported

    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
    Negative Logits
    Supported
    -0.74
    supported
    -0.70
     mergeFrom
    -0.67
     Supported
    -0.65
    PullParser
    -0.64
     supported
    -0.63
    AnimationsModule
    -0.63
    PhysRev
    -0.56
    ArrowToggle
    -0.54
    Вопросы
    -0.54
    POSITIVE LOGITS
     by
    0.77
     تانيه
    0.68
     EconPapers
    0.59
     living
    0.54
     Living
    0.53
     numerus
    0.52
    DoubleQuotes
    0.51
    Referanser
    0.50
    bolista
    0.50
     Fluent
    0.46
    Activations Density 0.003%

    No Known Activations