© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38734
    Prev
    Next
    INDEX
    Explanations

    industry

    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
     strip
    -0.65
     Industry
    -0.60
    speakers
    -0.51
    SPEAKER
    -0.51
     députés
    -0.49
    speaker
    -0.48
     fumée
    -0.48
    street
    -0.47
     street
    -0.46
     fuite
    -0.46
    POSITIVE LOGITS
     дописавши
    0.97
     समीक्षक
    0.85
    tagHelperRunner
    0.78
    ISupport
    0.75
    DockStyle
    0.68
    IsContent
    0.64
    rån
    0.63
    Ссылки
    0.62
    ///</
    0.60
    BeginInit
    0.60
    Activations Density 1.568%

    No Known Activations