© 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. 0-CLT-HP
    7. 93673
    Prev
    Next
    INDEX
    Explanations

    research

    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
    Datuak
    -1.22
     يتيمه
    -1.09
     فريبيس
    -1.07
     ModelExpression
    -1.01
     للمعارف
    -1.00
    RegressionTest
    -0.96
    Personensuche
    -0.94
     beginnetje
    -0.94
     bezeichneter
    -0.94
     виправивши
    -0.93
    POSITIVE LOGITS
     at
    0.68
     and
    0.62
     from
    0.61
     in
    0.58
     research
    0.57
     presented
    0.56
     conducted
    0.54
     investigating
    0.52
     identified
    0.50
     investigated
    0.50
    Activations Density 0.001%

    No Known Activations