© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11850
    Prev
    Next
    INDEX
    Explanations

    MAR

    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
     MAR
    -0.54
     BorderRadius
    -0.50
     writeTo
    -0.50
     ospiti
    -0.49
     useAppContext
    -0.49
    zust
    -0.48
    MAR
    -0.48
     tratti
    -0.47
    TagHelper
    -0.47
     Paglinawan
    -0.47
    POSITIVE LOGITS
     estekak
    0.60
    ContentAsync
    0.54
    letch
    0.54
    bootstrapcdn
    0.54
    Autoritní
    0.54
     cha
    0.52
     gild
    0.52
    chequer
    0.50
    keted
    0.50
    skosten
    0.50
    Activations Density 0.049%

    No Known Activations