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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91893
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific documents

    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
    thers
    -0.65
    ing
    -0.46
    1
    -0.44
     front
    -0.42
     onu
    -0.41
    .
    -0.40
     number
    -0.39
    onk
    -0.39
    ↵
    -0.38
    ForRow
    -0.38
    POSITIVE LOGITS
    ]")]
    0.95
     Roskov
    0.92
    EndContext
    0.79
     ویکی‌پدیای
    0.78
     Waray
    0.78
    Tikang
    0.77
    valdi
    0.75
     وتسجيلات
    0.75
     //$
    0.74
    IndentedString
    0.73
    Activations Density 0.104%

    No Known Activations