© 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. 20-CLT-HP
    7. 74593
    Prev
    Next
    INDEX
    Explanations

    were

    np_max-act-logits · 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
     onOptions
    -0.55
    aarrggbb
    -0.53
    ElementException
    -0.49
    memoized
    -0.46
    XmlRootElement
    -0.45
    velocityX
    -0.42
    kreises
    -0.41
     TextAppearance
    -0.41
    tudes
    -0.40
     Gar
    -0.39
    POSITIVE LOGITS
    +#+
    0.77
     won
    0.76
    Tembelea
    0.73
    won
    0.67
     архивлан
    0.65
    IntoConstraints
    0.65
     greateſt
    0.64
    Won
    0.63
    :+:
    0.61
    #+#
    0.59
    Activations Density 0.002%

    No Known Activations