© 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. 0-CLT-HP
    7. 1551
    Prev
    Next
    INDEX
    Explanations

    due

    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
    mi
    -0.69
    due
    -0.66
    ly
    -0.65
    ostante
    -0.64
     AppColors
    -0.64
     Reſ
    -0.60
     Houſe
    -0.60
     Scip
    -0.60
    ճ
    -0.60
     greateſt
    -0.59
    POSITIVE LOGITS
    ClientSize
    0.60
     betweenstory
    0.60
    MessageTagHelper
    0.59
     INTERESAR
    0.57
     Obrador
    0.56
     препратки
    0.55
    webElement
    0.54
     Commencez
    0.54
    !*\
    0.54
    cshtml
    0.53
    Activations Density 0.092%

    No Known Activations