© 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. 93798
    Prev
    Next
    INDEX
    Explanations

    president

    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
    <eos>
    -0.59
     President
    -0.57
     president
    -0.54
    age
    -0.47
    stone
    -0.47
     (
    -0.45
    on
    -0.43
     T
    -0.43
    en
    -0.42
    ie
    -0.42
    POSITIVE LOGITS
     Efq
    0.93
     وتسجيلات
    0.82
    ScopeManager
    0.80
     myſelf
    0.80
     photolibrary
    0.79
     himſelf
    0.79
    ſelf
    0.79
     Majefty
    0.79
     насељу
    0.79
     doubtnut
    0.78
    Activations Density 0.093%

    No Known Activations