© 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. 1-CLT-HP
    7. 15877
    Prev
    Next
    INDEX
    Explanations

    m

    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
    ⓧ
    -0.68
     kasarigan
    -0.60
    parsedMessage
    -0.59
    Personensuche
    -0.55
    Clik
    -0.54
     Paglinawan
    -0.54
    IActionResult
    -0.52
     الاطلاع
    -0.49
    UnknownFieldSet
    -0.49
     bargain
    -0.49
    POSITIVE LOGITS
    kammer
    0.61
    ErrorListener
    0.54
    orElseThrow
    0.53
    claration
    0.52
    lantern
    0.52
     Basement
    0.52
     Just
    0.52
    漓
    0.52
    sprechend
    0.52
     élo
    0.51
    Activations Density 0.035%

    No Known Activations