© 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. 4-CLT-HP
    7. 4937
    Prev
    Next
    INDEX
    Explanations

    of

    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
     frequenza
    -0.46
     aikaa
    -0.43
    träd
    -0.42
    lenir
    -0.41
     pauvres
    -0.41
     Erişim
    -0.41
    îtra
    -0.41
     garçons
    -0.40
     bocca
    -0.40
     igjen
    -0.40
    POSITIVE LOGITS
     Roskov
    0.82
     propOrder
    0.79
     all
    0.77
    elemField
    0.77
    \{\\
    0.75
     >=",
    0.69
    JsonFormat
    0.67
    __*/
    0.66
    setVerticalGroup
    0.65
    memoized
    0.63
    Activations Density 0.004%

    No Known Activations