© 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. 4-CLT-HP
    7. 2744
    Prev
    Next
    INDEX
    Explanations

    Gu

    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
    DOCTYPE
    -0.67
     BoxDecoration
    -0.55
    énario
    -0.54
     cref
    -0.50
    migrationBuilder
    -0.50
    XmlType
    -0.50
     Oppen
    -0.49
    ullo
    -0.49
    ObjectModel
    -0.48
     opérés
    -0.48
    POSITIVE LOGITS
     noDo
    0.59
    fromnode
    0.56
     <=",
    0.55
     pă
    0.51
     chande
    0.50
     Roskov
    0.50
    RegressionTest
    0.50
     saites
    0.49
    abetta
    0.49
    Unused
    0.49
    Activations Density 0.002%

    No Known Activations