© 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. 0-CLT-HP
    7. 90437
    Prev
    Next
    INDEX
    Explanations

    called

    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
     called
    -1.69
    called
    -1.46
     llamado
    -1.42
     chamado
    -1.28
     llamados
    -1.23
     llamada
    -1.20
     denominado
    -1.16
     appelée
    -1.14
     appelé
    -1.13
     chamada
    -1.13
    POSITIVE LOGITS
    RegressionTest
    1.13
    MigrationBuilder
    1.00
    Autoritní
    0.91
    __':
    0.89
    __':
    0.88
     kaarangay
    0.83
    XMLSchema
    0.82
    ArrowToggle
    0.82
    queryInterface
    0.81
    apimachinery
    0.80
    Activations Density 0.033%

    No Known Activations