© 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. 1-CLT-HP
    7. 9892
    Prev
    Next
    INDEX
    Explanations

    Royalty

    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
    ThroughAttribute
    -0.61
     Paglinawan
    -0.57
    ypeł
    -0.57
    %");
    -0.56
     électroniques
    -0.55
     mené
    -0.54
    Seeder
    -0.54
     organisée
    -0.53
    
    -0.52
     soutenu
    -0.52
    POSITIVE LOGITS
     المعيارى
    0.71
     initComponents
    0.54
    kuuta
    0.52
     EClass
    0.51
    groom
    0.47
    נגלית
    0.46
    featureID
    0.45
     kaarangay
    0.45
    dataIndex
    0.44
    avía
    0.44
    Activations Density 0.010%

    No Known Activations