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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97085
    Prev
    Next
    INDEX
    Explanations

    occupations

    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
     chefs
    -0.88
     teachers
    -0.81
    Driver
    -0.81
    chef
    -0.81
     shepherd
    -0.81
    pherd
    -0.80
     shepherds
    -0.79
     chef
    -0.76
     Driver
    -0.75
     pilote
    -0.75
    POSITIVE LOGITS
     ویکی‌پدی
    0.68
    🏽
    0.67
    esModule
    0.66
     AssemblyVersion
    0.62
    🏾
    0.61
    fontawesome
    0.60
     HasFactory
    0.60
    ByExample
    0.60
    WillAppear
    0.59
    🏼
    0.58
    Activations Density 0.559%

    No Known Activations