© 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. 5-CLT-HP
    7. 95141
    Prev
    Next
    INDEX
    Explanations

    cold

    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
     للاسماء
    -0.87
     utafitiHapana
    -0.80
    SPATH
    -0.73
    تفصیلات
    -0.70
    ArgsConstructor
    -0.66
     tärke
    -0.65
    rozum
    -0.65
     ComVisible
    -0.65
     onCancelled
    -0.65
    navbar
    -0.63
    POSITIVE LOGITS
    Према
    0.43
    LayoutStyle
    0.42
    TagMode
    0.39
    ayne
    0.39
    letin
    0.37
    ster
    0.36
    casian
    0.35
    iters
    0.34
    bello
    0.33
    prüche
    0.33
    Activations Density 0.001%

    No Known Activations