© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74494
    Prev
    Next
    INDEX
    Explanations

    Good

    np_max-act-logits · 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
     بيها
    -0.58
     SIMBAD
    -0.57
     autorytatywna
    -0.56
     يتيمه
    -0.52
    RenderAtEndOf
    -0.50
    olsom
    -0.48
     mime
    -0.48
    rawtypes
    -0.47
    soli
    -0.47
     core
    -0.46
    POSITIVE LOGITS
     EconPapers
    0.55
    
    0.54
    ).__
    0.51
     /\.(
    0.51
    VersionUID
    0.49
    CHI
    0.47
     abuso
    0.47
    chi
    0.46
     שוליים
    0.46
    typeparam
    0.45
    Activations Density 0.000%

    No Known Activations