© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 5554
    Prev
    Next
    INDEX
    Explanations

    effect

    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
     Ceramby
    -0.56
     Ancona
    -0.53
    suma
    -0.53
    ونا
    -0.50
     Reun
    -0.47
    Gön
    -0.47
    atown
    -0.47
    RuleContext
    -0.47
    tagHelperRunner
    -0.47
     Eton
    -0.46
    POSITIVE LOGITS
    IsMutable
    0.55
     AppComponent
    0.55
    λευτα
    0.52
     SwitchCompat
    0.51
     Púb
    0.51
    alcoholic
    0.49
    TextHelper
    0.49
    !("{}",
    0.49
     بيها
    0.49
    гинал
    0.49
    Activations Density 0.012%

    No Known Activations