© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95086
    Prev
    Next
    INDEX
    Explanations

    Web scraping or names

    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
    ters
    -0.87
     Lan
    -0.85
    Lan
    -0.75
     scrape
    -0.72
     scraping
    -0.71
     Scrap
    -0.69
     low
    -0.68
    low
    -0.68
     Low
    -0.65
    Low
    -0.65
    POSITIVE LOGITS
    CloseOperation
    0.76
    Искәрмәләр
    0.60
    mergeFrom
    0.59
     незавершена
    0.58
    ValueStyle
    0.54
    دانشنامهٔ
    0.54
    saraba
    0.53
    cinia
    0.52
    }],
    0.52
    WithIOException
    0.52
    Activations Density 0.546%

    No Known Activations