© 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. 4-CLT-HP
    7. 1
    Prev
    Next
    INDEX
    Explanations

    terms

    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
     or
    -0.52
     doInBackground
    -0.49
    knex
    -0.49
     թվական
    -0.47
    createServer
    -0.47
    úgó
    -0.46
     popcorn
    -0.46
     BitmapFactory
    -0.46
    Nationalité
    -0.45
    executeUpdate
    -0.44
    POSITIVE LOGITS
     betweenstory
    0.59
     समीक्षक
    0.56
     transférez
    0.56
     kaarangay
    0.54
    تفصیلات
    0.52
    InInspector
    0.52
     कैसी
    0.52
    ByExample
    0.51
    THING
    0.51
     desenli
    0.49
    Activations Density 0.000%

    No Known Activations