© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6133
    Prev
    Next
    INDEX
    Explanations

    on

    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
    Negative Logits
     StatefulWidget
    -0.69
    Personendaten
    -0.65
    IsMutable
    -0.65
    Tikang
    -0.60
    richTextPanel
    -0.59
     kasarigan
    -0.59
     שוליים
    -0.58
     StatelessWidget
    -0.58
     BoxFit
    -0.57
     اطلع
    -0.56
    POSITIVE LOGITS
    piles
    0.54
     significance
    0.54
    ionato
    0.49
    styleType
    0.48
     Profession
    0.47
    Abp
    0.47
    glob
    0.46
    ismer
    0.46
    xFFFFFF
    0.45
    imod
    0.45
    Activations Density 0.001%

    No Known Activations