© 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. 5-CLT-HP
    7. 4125
    Prev
    Next
    INDEX
    Explanations

    of

    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
     the
    -0.83
     this
    -0.59
     those
    -0.55
     your
    -0.55
    jsonwebtoken
    -0.54
     things
    -0.54
     concepts
    -0.54
     समीक्षाओं
    -0.54
     these
    -0.53
     cakes
    -0.53
    POSITIVE LOGITS
     épaules
    0.79
     négociations
    0.69
     côtés
    0.63
     oreilles
    0.60
     prisonniers
    0.59
     lèvres
    0.59
     réfugiés
    0.59
     lumières
    0.58
     ouvriers
    0.58
    暂无
    0.57
    Activations Density 0.002%

    No Known Activations