© 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. 95115
    Prev
    Next
    INDEX
    Explanations

    academic texts

    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
     ब्रेकडाउन
    -0.71
    ，“
    -0.69
    
    -0.66
     σ
    -0.63
    domada
    -0.62
    ……"
    -0.61
    ”.
    -0.61
    getline
    -0.60
    dames
    -0.60
     समीक्षक
    -0.59
    POSITIVE LOGITS
    AndEndTag
    0.48
    DockStyle
    0.42
     typelib
    0.42
    دانشنامهٔ
    0.42
     виправивши
    0.40
    JspWriter
    0.39
    клопе
    0.38
    Географија
    0.37
    tivi
    0.35
    <eos>
    0.34
    Activations Density 0.000%

    No Known Activations