© 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. 5-CLT-HP
    7. 95255
    Prev
    Next
    INDEX
    Explanations

    laws and acts

    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
     nakalista
    -1.10
     HasFactory
    -0.71
    webElementXpaths
    -0.69
    +#+#
    -0.69
    ContentAsync
    -0.63
     生命周期
    -0.62
    brido
    -0.61
    ranean
    -0.59
    RUnlock
    -0.59
    principalTable
    -0.58
    POSITIVE LOGITS
     by
    0.46
     passing
    0.44
     September
    0.44
     October
    0.42
    atguigu
    0.42
     August
    0.42
    LayoutStyle
    0.41
     April
    0.41
     thereby
    0.41
    isNotBlank
    0.41
    Activations Density 0.001%

    No Known Activations