© 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. 3194
    Prev
    Next
    INDEX
    Explanations

    that

    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
     and
    -0.59
     så
    -0.51
    AxisAlignment
    -0.50
     ditemui
    -0.43
     but
    -0.42
    WebElementEntity
    -0.42
    RegressionTest
    -0.41
    ₂,
    -0.40
     so
    -0.39
    SourceChecksum
    -0.38
    POSITIVE LOGITS
     includes
    0.82
    ’
    0.79
     is
    0.79
     disambiguazione
    0.73
    '
    0.72
    DoubleQuotes
    0.71
     nahilalakip
    0.70
    MENAFN
    0.70
     sucks
    0.67
     Theſe
    0.67
    Activations Density 0.003%

    No Known Activations