© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92783
    Prev
    Next
    INDEX
    Explanations

    fetch

    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
     resourceCulture
    -0.91
    DockStyle
    -0.91
    setVerticalGroup
    -0.84
     estimés
    -0.83
    الحياه
    -0.75
     ModelExpression
    -0.73
     disambiguazione
    -0.70
     pleaſure
    -0.69
    ize
    -0.67
     Мексичка
    -0.67
    POSITIVE LOGITS
    y
    0.67
    ின
    0.60
    e
    0.56
     goods
    0.55
    a
    0.54
    ment
    0.54
    Sí
    0.53
    i
    0.50
    奥
    0.48
     Albion
    0.47
    Activations Density 1.751%

    No Known Activations