© 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. 0-CLT-HP
    7. 94926
    Prev
    Next
    INDEX
    Explanations

    prepared

    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
     للاسماء
    -0.90
     Paglinawan
    -0.80
     Chwiliwch
    -0.72
    Personensuche
    -0.71
    tagHelperRunner
    -0.70
     preparación
    -0.69
     persiapan
    -0.69
    Préparation
    -0.68
     preparazione
    -0.68
    WithIOException
    -0.68
    POSITIVE LOGITS
     chemical
    0.55
     formula
    0.54
     machine
    0.53
     chemicals
    0.51
     rating
    0.50
     Machine
    0.48
     lys
    0.48
     fior
    0.48
     frequency
    0.47
     Runs
    0.47
    Activations Density 0.965%

    No Known Activations