© 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. 45113
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    sibility
    -0.76
     hoof
    -0.65
    zens
    -0.61
    heits
    -0.61
    redo
    -0.48
     horseshoe
    -0.46
    Explanation
    -0.45
    󠁴
    -0.45
    FDRE
    -0.45
     أج
    -0.43
    POSITIVE LOGITS
     الحره
    0.75
     تضيفلها
    0.69
    expandindo
    0.67
    CppMethod
    0.60
    salut
    0.59
    sport
    0.58
    )++;
    0.57
    WireFormatLite
    0.57
    TagMode
    0.57
    Искәрмәләр
    0.56
    Activations Density 1.850%

    No Known Activations