© 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. 38997
    Prev
    Next
    INDEX
    Explanations

    buildings

    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
    脚注の使い方
    -0.66
    ⓧ
    -0.66
     resourceCulture
    -0.61
    حوالہ
    -0.60
     HasFactory
    -0.59
    tvguidetime
    -0.59
    twimg
    -0.58
    jsxFileName
    -0.57
     Assumptions
    -0.57
    StructEnd
    -0.56
    POSITIVE LOGITS
    клопе
    0.54
    ్రామ
    0.50
    windowFixed
    0.48
     年代
    0.47
    iedział
    0.46
    <bos>
    0.45
     bezeich
    0.45
     specialised
    0.45
     narrated
    0.45
    entrale
    0.44
    Activations Density 0.039%

    No Known Activations