© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45665
    Prev
    Next
    INDEX
    Explanations

    uat

    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
    lapse
    -0.74
    uat
    -0.60
    SourceChecksum
    -0.59
    didSet
    -0.56
    सन्दर्भ
    -0.56
    tagHelperRunner
    -0.56
    olone
    -0.55
    canActivate
    -0.55
    SaveVideo
    -0.55
    ($__
    -0.54
    POSITIVE LOGITS
     kasarigan
    0.54
    BagLayout
    0.52
     aveug
    0.49
     heut
    0.49
     Orrell
    0.48
     vœux
    0.48
     informée
    0.45
     Driver
    0.45
    Intérieur
    0.44
    schra
    0.44
    Activations Density 0.011%

    No Known Activations