© 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. 4-CLT-HP
    7. 554
    Prev
    Next
    INDEX
    Explanations

    doll

    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
    tagHelperRunner
    -0.97
     CreateTagHelper
    -0.90
    Personensuche
    -0.80
     समीक्षाओं
    -0.80
     оригіналу
    -0.75
    TagMode
    -0.75
    :✨
    -0.74
     kaynağından
    -0.71
    MLLoader
    -0.71
     MainAxisSize
    -0.71
    POSITIVE LOGITS
     spoiling
    0.44
    spo
    0.43
    zeb
    0.42
     sæ
    0.42
     spoil
    0.42
    Consumed
    0.41
     ho
    0.41
    nus
    0.41
    ilus
    0.40
    bou
    0.40
    Activations Density 0.745%

    No Known Activations