© 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. 90981
    Prev
    Next
    INDEX
    Explanations

    code

    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
    uterte
    -0.44
    textbackslash
    -0.44
    ,
    -0.44
    IELD
    -0.44
    adaptiveStyles
    -0.43
    ỏi
    -0.43
    ệu
    -0.41
    stalt
    -0.41
    靖
    -0.41
    cua
    -0.41
    POSITIVE LOGITS
     autorytatywna
    0.78
     myſelf
    0.73
    AndEndTag
    0.71
    LLocation
    0.68
     ویکی‌پدیا
    0.66
     resourceCulture
    0.65
     themſelves
    0.65
     виправивши
    0.65
    
    0.63
    InstrumentedTest
    0.63
    Activations Density 0.085%

    No Known Activations