© 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. 72592
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    MLLoader
    -0.80
    RegressionTest
    -0.65
    enumi
    -0.60
    setVerticalGroup
    -0.59
     становника
    -0.55
     TextAlign
    -0.53
    éez
    -0.53
     AFA
    -0.52
     initComponents
    -0.52
    IMPORTED
    -0.51
    POSITIVE LOGITS
     ligiloj
    0.66
     Waray
    0.50
     ejecuta
    0.44
     canadensis
    0.44
     архивлан
    0.44
     normal
    0.43
     pat
    0.43
    }{#
    0.42
    قدر
    0.41
     yöne
    0.41
    Activations Density 0.000%

    No Known Activations