© 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. 12208
    Prev
    Next
    INDEX
    Explanations

    Code and file management

    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
    verdi
    -2.11
     verdi
    -0.61
     terle
    -0.55
    spl
    -0.54
    ]++;
    -0.53
    wert
    -0.52
    ardless
    -0.47
    skon
    -0.46
    hards
    -0.46
    value
    -0.46
    POSITIVE LOGITS
    kháu
    0.72
    StructEnd
    0.69
     GeoNames
    0.65
    PMailer
    0.64
    脚注の使い方
    0.62
    TintMode
    0.61
    intios
    0.61
     Himo
    0.61
     kasarigan
    0.59
    Спасылкі
    0.59
    Activations Density 0.008%

    No Known Activations