© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74991
    Prev
    Next
    INDEX
    Explanations

    comparison of degree

    np_max-act-logits · 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
     незавершена
    -0.84
     Majefty
    -0.74
    asgi
    -0.70
     pleaſure
    -0.66
     InputDecoration
    -0.66
     Jefus
    -0.66
    bootstrapcdn
    -0.64
     caufe
    -0.64
    hyrchwyd
    -0.62
    VersionUID
    -0.61
    POSITIVE LOGITS
     relatively
    0.94
     way
    0.94
     comparatively
    0.83
     Relatively
    0.82
    relatively
    0.78
     far
    0.69
     Way
    0.68
    way
    0.66
    Way
    0.63
     low
    0.62
    Activations Density 0.001%

    No Known Activations