Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 98267
    Prev
    Next
    INDEX
    Explanations

    fragmented information

    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
     most
    -1.15
    most
    -0.92
    Most
    -0.75
     MOST
    -0.69
     Most
    -0.67
    MOST
    -0.66
    unk
    -0.54
     EventEmitter
    -0.53
    Становништво
    -0.52
    ณ์
    -0.51
    POSITIVE LOGITS
    sizeCache
    0.70
    :✨
    0.69
     métallique
    0.66
    findpost
    0.61
    ^(@)
    0.60
     paroisse
    0.60
     ſhe
    0.59
     Efq
    0.59
    illage
    0.59
    RuleContext
    0.59
    Activations Density 1.629%

    No Known Activations