© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93544
    Prev
    Next
    INDEX
    Explanations

    punctuation and "and"

    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
     AssemblyCulture
    -0.66
    tvguidetime
    -0.65
    出版年
    -0.64
    
    -0.59
    Tembelea
    -0.54
    Välislingid
    -0.53
    alamu
    -0.53
    Rujuakan
    -0.51
    CppMethod
    -0.51
    Lähteet
    -0.51
    POSITIVE LOGITS
    Capítulo
    0.50
     ThemeData
    0.46
     zä
    0.46
     HasFactory
    0.46
    quartered
    0.44
     Siamo
    0.42
    Geplaatst
    0.41
    eseorang
    0.41
     متحده
    0.40
     MCS
    0.40
    Activations Density 0.022%

    No Known Activations