© 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. 1-CLT-HP
    7. 277
    Prev
    Next
    INDEX
    Explanations

    Mary

    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
     Mary
    -0.93
     Marys
    -0.71
    Mary
    -0.69
     the
    -0.55
    ably
    -0.54
    клопе
    -0.54
     mary
    -0.53
     MARY
    -0.52
     future
    -0.50
    mary
    -0.49
    POSITIVE LOGITS
    Espèce
    0.59
     TextInputType
    0.59
     Lumia
    0.58
     Мексичка
    0.57
     épais
    0.55
    openConnection
    0.54
     CURIAM
    0.53
     almoço
    0.52
    WRENCE
    0.52
     bezeichneter
    0.51
    Activations Density 0.023%

    No Known Activations