© 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. 96429
    Prev
    Next
    INDEX
    Explanations

    amounts and quantities

    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
    MigrationBuilder
    -0.60
    AutoScaleMode
    -0.60
     ModelExpression
    -0.56
     indisponible
    -0.55
    رشف
    -0.54
    Composable
    -0.53
    invokeLater
    -0.52
    fjspx
    -0.52
    EndGlobalSection
    -0.50
     Waw
    -0.50
    POSITIVE LOGITS
    MessageTagHelper
    0.56
     kahve
    0.50
     it
    0.48
     Turquie
    0.47
    terase
    0.47
     tjen
    0.46
     Finlande
    0.46
    cuterie
    0.46
    unhofer
    0.44
     espagnole
    0.44
    Activations Density 0.001%

    No Known Activations