© 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. 93189
    Prev
    Next
    INDEX
    Explanations

    principal

    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
    Principal
    -0.50
     nhàng
    -0.50
     Principal
    -0.50
     principal
    -0.48
    gtest
    -0.47
    InitStruct
    -0.47
    nezeu
    -0.45
    ########.
    -0.45
     Tuhan
    -0.45
    createServer
    -0.44
    POSITIVE LOGITS
     Daß
    0.70
    Gön
    0.65
     propOrder
    0.62
    קישורים
    0.58
    تفصیلات
    0.58
    Autoritní
    0.57
    참고
    0.57
     Krakowie
    0.57
     MatDialog
    0.56
     Signalez
    0.55
    Activations Density 0.704%

    No Known Activations