© 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. 20-CLT-HP
    7. 77692
    Prev
    Next
    INDEX
    Explanations

    scientific/technical language

    np_max-act-logits · 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
    FormTagHelper
    -0.75
    تفصیلات
    -0.71
    Personensuche
    -0.69
    GEBURTSDATUM
    -0.63
    település
    -0.61
     متعلقه
    -0.59
     Савезне
    -0.57
     Italijanski
    -0.57
     Económica
    -0.56
    Tikang
    -0.56
    POSITIVE LOGITS
    jsdelivr
    0.56
     length
    0.47
     penet
    0.47
     TRO
    0.45
    <>("
    0.43
    setLength
    0.43
     Sd
    0.42
     Huy
    0.42
    ipedi
    0.41
    вится
    0.40
    Activations Density 0.002%

    No Known Activations