© 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. 5-CLT-HP
    7. 96570
    Prev
    Next
    INDEX
    Explanations

    copyright and corporations

    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
     تانيه
    -0.71
     незавершена
    -0.62
    RenderAtEndOf
    -0.61
    himovic
    -0.60
     وتسجيلات
    -0.59
    ]-'
    -0.57
    UnusedPrivate
    -0.56
    ыгана
    -0.56
    GEBURTS
    -0.56
    ectoria
    -0.55
    POSITIVE LOGITS
     
    0.60
    2
    0.57
    findpost
    0.53
     sahiptir
    0.49
    <thead>
    0.48
     nélkül
    0.48
    antd
    0.48
     numéros
    0.46
     copies
    0.46
     Inscrivez
    0.46
    Activations Density 0.120%

    No Known Activations