© 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. 44078
    Prev
    Next
    INDEX
    Explanations

    starting from zero, considering

    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
    $_['
    -0.62
    mind
    -0.59
     mind
    -0.59
    ſelf
    -0.59
    ſelves
    -0.57
     maroca
    -0.57
     kapturem
    -0.56
     tremp
    -0.56
    Step
    -0.56
     acrylique
    -0.55
    POSITIVE LOGITS
    ToBounds
    0.69
    下载附件
    0.60
     препратки
    0.56
     propOrder
    0.56
    dafx
    0.54
     CreateTagHelper
    0.54
    Hozzáférés
    0.52
     שוליים
    0.52
    〉
    0.52
    rophes
    0.51
    Activations Density 1.481%

    No Known Activations