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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92058
    Prev
    Next
    INDEX
    Explanations

    patterns, surfaces, or textures

    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
    rrggbb
    -0.64
    ukone
    -0.63
     tiles
    -0.62
    <thead>
    -0.61
     onCreateView
    -0.61
    ttino
    -0.59
    Jeografia
    -0.59
    til
    -0.57
    oneofs
    -0.57
    ordinator
    -0.57
    POSITIVE LOGITS
    s
    1.10
    ی
    0.63
    ness
    0.59
    sun
    0.57
     Perſ
    0.55
    esis
    0.54
    epy
    0.52
    ical
    0.52
    uality
    0.52
    ies
    0.51
    Activations Density 0.091%

    No Known Activations