© 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. 1-CLT-HP
    7. 320
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    1
    -0.49
    2
    -0.46
    <strong>
    -0.45
    <b>
    -0.41
    (
    -0.39
    4
    -0.37
    <em>
    -0.36
    6
    -0.36
    [
    -0.35
    3
    -0.35
    POSITIVE LOGITS
    ValueStyle
    0.90
    دانشنامهٔ
    0.88
    脚注の使い方
    0.87
     estimés
    0.87
    sizeCache
    0.86
    TagMode
    0.83
    %\]
    0.83
    хьтан
    0.82
    BibitemShut
    0.82
    :✨
    0.82
    Activations Density 0.135%

    No Known Activations