© 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. 92319
    Prev
    Next
    INDEX
    Explanations

    {

    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
    allos
    -0.63
    Välislingid
    -0.57
     def
    -0.54
    VideoCapture
    -0.51
    nanoTime
    -0.48
     form
    -0.47
    RegressionTest
    -0.47
    AlterField
    -0.47
    dede
    -0.47
     pilot
    -0.47
    POSITIVE LOGITS
    Портал
    0.61
    ,‎
    0.58
    GeneratedMessage
    0.57
     jadx
    0.57
    QPalette
    0.57
     endblock
    0.56
    weighed
    0.56
    __":
    0.55
    makedirs
    0.54
     Pyram
    0.51
    Activations Density 1.377%

    No Known Activations