© 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. 0-CLT-HP
    7. 94154
    Prev
    Next
    INDEX
    Explanations

    a

    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
     few
    -0.82
     new
    -0.77
     particular
    -0.75
     lot
    -0.75
     large
    -0.74
     special
    -0.73
     single
    -0.72
     very
    -0.71
     great
    -0.71
     certain
    -0.70
    POSITIVE LOGITS
     amitié
    0.85
     sagesse
    0.82
     efficacité
    0.81
     bonté
    0.81
     économie
    0.79
     autorité
    0.78
     dignité
    0.77
     ujednoznacz
    0.76
     obiettivo
    0.76
     وتسجيلات
    0.75
    Activations Density 0.249%

    No Known Activations