© 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. 4-CLT-HP
    7. 1987
    Prev
    Next
    INDEX
    Explanations

    plain

    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
    WebServlet
    -0.71
    AutoScale
    -0.68
    +#+#
    -0.66
    .*")]
    -0.62
    abestanden
    -0.60
     JADX
    -0.57
     onPostExecute
    -0.55
     незавершена
    -0.54
    :+:
    -0.54
    </thead>
    -0.54
    POSITIVE LOGITS
    tive
    0.77
    ness
    0.75
    tiveness
    0.67
    tiff
    0.64
    tively
    0.61
    clothes
    0.61
    spoken
    0.60
    est
    0.60
    folk
    0.59
     folk
    0.58
    Activations Density 0.006%

    No Known Activations