© 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. 43367
    Prev
    Next
    INDEX
    Explanations

    Introduction paragraphs

    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
    gée
    -0.48
     разве
    -0.48
     coffe
    -0.47
    অ
    -0.47
    приятия
    -0.47
     أث
    -0.46
     CURLOPT
    -0.45
     occorre
    -0.45
     lagu
    -0.45
    Few
    -0.45
    POSITIVE LOGITS
     unknownFields
    0.78
    CppMethod
    0.75
    aarrggbb
    0.71
    الإنجليزية
    0.68
     bParam
    0.64
     Réponses
    0.61
     htons
    0.61
     mxArray
    0.61
     CreateTagHelper
    0.60
    ResumeLayout
    0.59
    Activations Density 1.527%

    No Known Activations