Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97882
    Prev
    Next
    INDEX
    Explanations

    industries

    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
     industry
    -1.86
    industry
    -1.62
    Industry
    -1.57
     Industry
    -1.49
     INDUSTRY
    -1.44
     industries
    -1.42
    INDUSTRY
    -1.27
     industria
    -1.13
    行业
    -1.04
     indústria
    -1.02
    POSITIVE LOGITS
     متعلقه
    0.79
     of
    0.75
    WithIOException
    0.57
    BeginContext
    0.55
     بيها
    0.52
    реди
    0.51
     onlyOwner
    0.51
    ()(
    0.50
     оригіналу
    0.50
    Pratique
    0.50
    Activations Density 0.086%

    No Known Activations