© 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. 0-CLT-HP
    7. 39967
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
     Profit
    -0.66
    profit
    -0.63
     profit
    -0.56
    Profit
    -0.53
    gen
    -0.50
    super
    -0.49
    port
    -0.48
    破
    -0.46
     La
    -0.46
    وى
    -0.45
    POSITIVE LOGITS
    PreferredItem
    0.82
    cèse
    0.81
    InjectAttribute
    0.77
    HasAnnotation
    0.77
    KURZBESCHREIBUNG
    0.75
     ModelExpression
    0.73
    verwijspagina
    0.71
    Personensuche
    0.70
    preloader
    0.70
     kasarigan
    0.69
    Activations Density 0.216%

    No Known Activations