© 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. 4-CLT-HP
    7. 3515
    Prev
    Next
    INDEX
    Explanations

    numerical dates

    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
     Normdatei
    -0.89
     pulumi
    -0.62
    帖最后由
    -0.61
    ecap
    -0.60
    TagMode
    -0.58
     الدولى
    -0.57
    astify
    -0.56
     Lockhart
    -0.54
     republican
    -0.54
     المعيارى
    -0.54
    POSITIVE LOGITS
     for
    0.65
    .
    0.60
     per
    0.52
     "
    0.52
     (
    0.51
    Diwedd
    0.51
    Tikang
    0.50
    ServletConfig
    0.50
    rigated
    0.49
    EndInit
    0.49
    Activations Density 0.026%

    No Known Activations