© 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. 4633
    Prev
    Next
    INDEX
    Explanations

    while

    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
     Khrushchev
    -0.51
    øse
    -0.50
    calaure
    -0.47
    posób
    -0.47
     obsolete
    -0.46
     meant
    -0.45
    meant
    -0.45
    izop
    -0.45
     bí
    -0.45
    emit
    -0.45
    POSITIVE LOGITS
    脚注の使い方
    0.77
     youre
    0.67
     you
    0.66
     useParams
    0.61
    you
    0.60
    DockStyle
    0.60
     enjoying
    0.59
    parsedMessage
    0.57
    openzeppelin
    0.57
    FunctionFlags
    0.56
    Activations Density 0.010%

    No Known Activations