© 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. 5-CLT-HP
    7. 6182
    Prev
    Next
    INDEX
    Explanations

    of

    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
     course
    -0.54
    Rè
    -0.54
    álló
    -0.53
    ódó
    -0.50
    moduleName
    -0.47
    ImageContext
    -0.47
    ography
    -0.46
    IFICATE
    -0.44
     BehaviorSubject
    -0.43
    ategorien
    -0.43
    POSITIVE LOGITS
    Portale
    0.75
    localctx
    0.67
    úgó
    0.65
    клопе
    0.62
     Meksiku
    0.60
    ConstraintMaker
    0.58
     <=",
    0.57
    Hauptartikel
    0.57
    ）.
    0.56
    )$-
    0.55
    Activations Density 0.002%

    No Known Activations