© 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. 1-CLT-HP
    7. 13523
    Prev
    Next
    INDEX
    Explanations

    technology advancements

    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
    \)
    -1.07
    JsonHelper
    -0.57
    ISupport
    -0.56
     للاسماء
    -0.55
    HasForeignKey
    -0.55
    MemoryWarning
    -0.54
    AsyncResult
    -0.54
    orianCalendar
    -0.54
     épaules
    -0.53
    UnusedPrivate
    -0.53
    POSITIVE LOGITS
     ويكيپيديا
    0.50
     ivelany
    0.50
    gway
    0.47
     wickets
    0.47
    izes
    0.46
    toPromise
    0.46
     playgrounds
    0.45
    jface
    0.44
    hdysval
    0.43
    aventure
    0.43
    Activations Density 0.023%

    No Known Activations