© 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. 5-CLT-HP
    7. 223
    Prev
    Next
    INDEX
    Explanations

    factor VIII

    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
     ujednoznacz
    -0.70
     Monfieur
    -0.69
    存于互联网档案馆
    -0.65
     betweenstory
    -0.63
    GeoNames
    -0.63
    jestel
    -0.60
     TextAppearance
    -0.60
     Findlay
    -0.59
    ſelf
    -0.56
    aneity
    -0.56
    POSITIVE LOGITS
     AssemblyCulture
    0.60
    stdc
    0.54
    cinta
    0.45
    出版年
    0.43
    ussis
    0.43
     JAXB
    0.42
    #
    0.42
     cellpadding
    0.42
     Costume
    0.41
    simpleType
    0.41
    Activations Density 0.002%

    No Known Activations