© 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. 5-CLT-HP
    7. 2898
    Prev
    Next
    INDEX
    Explanations

    Ted

    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
    hebt
    -0.54
    ConstraintMaker
    -0.53
     kaynağından
    -0.52
    insee
    -0.48
     Dressed
    -0.47
     sarees
    -0.46
    godic
    -0.45
     measurements
    -0.44
     bags
    -0.44
    HasColumnType
    -0.44
    POSITIVE LOGITS
    +#+#
    0.67
    itinéraire
    0.59
     initComponents
    0.57
    WriteTagHelper
    0.56
    invokeLater
    0.55
    PageIndex
    0.55
     >=",
    0.51
    MigrationBuilder
    0.49
     StatefulWidget
    0.49
    LLocation
    0.48
    Activations Density 0.000%

    No Known Activations