© 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. 20-CLT-HP
    7. 73059
    Prev
    Next
    INDEX
    Explanations

    Great

    np_max-act-logits · 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
    msgTypes
    -0.77
    __':
    -0.77
     localObject
    -0.75
     ModelExpression
    -0.74
     getItemId
    -0.71
    RegressionTest
    -0.69
    MethodManager
    -0.68
     الرياضيه
    -0.67
    TagHelper
    -0.67
     Theſe
    -0.65
    POSITIVE LOGITS
    Zimbabwe
    0.41
     occhi
    0.40
     ivelany
    0.40
     imprimée
    0.40
     médicaux
    0.39
     africains
    0.38
     financières
    0.38
    Jeografia
    0.38
     ব
    0.38
     jasa
    0.38
    Activations Density 0.001%

    No Known Activations