© 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. 20-CLT-HP
    7. 74717
    Prev
    Next
    INDEX
    Explanations

    technical documentation/forums

    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
    SourceChecksum
    -0.82
     оригіналу
    -0.70
     AssemblyProduct
    -0.68
     صوتيه
    -0.68
    setVerticalGroup
    -0.68
     متعلقه
    -0.66
    MENAFN
    -0.66
    
    -0.63
     חיצוניים
    -0.63
    ="@+
    -0.63
    POSITIVE LOGITS
     used
    0.58
     cloned
    0.50
    UITableViewCell
    0.49
     Вікіпе
    0.48
     hitting
    0.47
    CartItem
    0.47
    agai
    0.46
     hits
    0.46
     imported
    0.46
     hit
    0.46
    Activations Density 0.004%

    No Known Activations