© 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. 43822
    Prev
    Next
    INDEX
    Explanations

    married

    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
     married
    -1.44
    married
    -1.05
     Married
    -0.91
    Married
    -0.72
     lawyer
    -0.67
    Sent
    -0.59
     casado
    -0.59
     verheiratet
    -0.59
     casada
    -0.58
     practicing
    -0.57
    POSITIVE LOGITS
     doInBackground
    0.79
     mante
    0.61
     Мексичка
    0.58
    RenderAtEndOf
    0.57
     AssemblyCompany
    0.56
    URLException
    0.54
    UpdateCommand
    0.52
    DataSnapshot
    0.52
    trique
    0.50
    getColumnIndex
    0.49
    Activations Density 0.113%

    No Known Activations