© 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. 20-CLT-HP
    7. 77398
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act-logits · 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
    +#+#
    -0.84
    AddTagHelper
    -0.81
     Meksiku
    -0.81
    GEBURTSDATUM
    -0.79
     дописавши
    -0.79
     autorytatywna
    -0.76
     للاسماء
    -0.76
     disambiguazione
    -0.75
     propOrder
    -0.75
     समीक्षक
    -0.73
    POSITIVE LOGITS
    borderRadius
    0.42
    ۇ
    0.42
     ye
    0.41
    ev
    0.41
    Ế
    0.41
    IConfiguration
    0.40
    intel
    0.40
    DAV
    0.39
    fficiency
    0.39
    [])
    0.39
    Activations Density 0.002%

    No Known Activations