© 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. 5-CLT-HP
    7. 2196
    Prev
    Next
    INDEX
    Explanations

    factory

    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
     nacionalidad
    -0.34
    glDisable
    -0.34
     trov
    -0.34
     témoins
    -0.34
    face
    -0.32
     potete
    -0.32
    extérieur
    -0.31
    性格
    -0.31
     referencia
    -0.31
     considérée
    -0.31
    POSITIVE LOGITS
    expandindo
    0.93
    ItemLayout
    0.89
     незавершена
    0.89
     autorytatywna
    0.85
    ⓧ
    0.84
     مشين
    0.83
    migrationBuilder
    0.83
     సౌకర్య
    0.81
    batore
    0.79
     AssemblyProduct
    0.78
    Activations Density 0.000%

    No Known Activations