© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43966
    Prev
    Next
    INDEX
    Explanations

    referred

    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
     referred
    -1.30
    referred
    -1.05
     termed
    -0.85
     called
    -0.66
     disebut
    -0.64
     rendered
    -0.61
     называется
    -0.59
    ferred
    -0.58
     referido
    -0.58
    called
    -0.54
    POSITIVE LOGITS
    Autoritní
    0.94
    GEBURTSDATUM
    0.88
    expandindo
    0.86
    MigrationBuilder
    0.81
     propOrder
    0.81
    verwijspagina
    0.73
    Derbyniad
    0.73
     Administrativna
    0.72
    +#+#
    0.71
    Hentet
    0.71
    Activations Density 0.035%

    No Known Activations