© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76324
    Prev
    Next
    INDEX
    Explanations

    Military and training

    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
    MigrationBuilder
    -0.82
    Datuak
    -0.80
    
    -0.77
    QMetaType
    -0.72
    UnknownFieldSet
    -0.69
    ThroughAttribute
    -0.69
    GEBURTSDATUM
    -0.68
    الإنجليزية
    -0.68
    SourceChecksum
    -0.68
    CodeAttribute
    -0.68
    POSITIVE LOGITS
     mano
    0.79
     basic
    0.70
     maneuvers
    0.62
     Basic
    0.59
    Basic
    0.54
    basic
    0.53
     maneuver
    0.50
     training
    0.50
     pre
    0.50
     proving
    0.49
    Activations Density 0.000%

    No Known Activations