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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13247
    Prev
    Next
    INDEX
    Explanations

    fat

    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
    ########.
    -0.78
    Tembelea
    -0.73
    aarrggbb
    -0.68
    Clik
    -0.64
    lihood
    -0.63
    ential
    -0.63
     ویکی‌پدیا
    -0.61
     voordeel
    -0.60
     disambiguazione
    -0.60
    issauga
    -0.59
    POSITIVE LOGITS
    }{*}{}
    0.54
     Kom
    0.50
    acord
    0.46
    webElementXpaths
    0.44
    toHaveBeenCalled
    0.44
     biotic
    0.43
     pon
    0.42
    Gemeinsame
    0.42
     Ko
    0.42
    XmlRootElement
    0.42
    Activations Density 0.103%

    No Known Activations