© 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. 5-CLT-HP
    7. 4993
    Prev
    Next
    INDEX
    Explanations

    0

    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
    وعة
    -0.48
    sidemargin
    -0.48
     برانيه
    -0.47
    ectoria
    -0.47
     betweenstory
    -0.46
    kket
    -0.45
     fell
    -0.44
     članak
    -0.44
     wik
    -0.44
     intStringLen
    -0.43
    POSITIVE LOGITS
    BeginContext
    0.60
     يتيمه
    0.57
     intptr
    0.55
    jsdelivr
    0.54
    isure
    0.53
    RegressionTest
    0.52
    '],
    0.50
    Koordinaten
    0.50
    ╗
    0.49
    amaño
    0.49
    Activations Density 0.898%

    No Known Activations