© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9161
    Prev
    Next
    INDEX
    Explanations

    carry

    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
    <bos>
    -1.31
    '
    -0.49
    \
    -0.34
    getJSONObject
    -0.34
    hObject
    -0.33
    shortcode
    -0.33
    [toxicity=0]
    -0.33
     ex
    -0.31
    updateOne
    -0.31
    Ча
    -0.31
    POSITIVE LOGITS
     EconPapers
    0.92
     Itself
    0.91
     CreateTagHelper
    0.87
     كومونز
    0.76
    vician
    0.72
    parsedMessage
    0.72
     Teas
    0.71
    EndContext
    0.71
    pushFollow
    0.71
    Tembelea
    0.70
    Activations Density 0.008%

    No Known Activations