© 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. 1816
    Prev
    Next
    INDEX
    Explanations

    household

    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
     household
    -1.13
     domestic
    -1.03
    household
    -0.93
     Domestic
    -0.86
     Household
    -0.85
    Household
    -0.84
    Domestic
    -0.81
    domestic
    -0.81
     the
    -0.72
     domés
    -0.61
    POSITIVE LOGITS
     ModelExpression
    0.90
    Xna
    0.79
     IndexPath
    0.77
    ReusableCell
    0.75
    .*")]
    0.74
    EndContext
    0.73
     LUMP
    0.71
    TargetException
    0.71
    )_/¯
    0.70
     الحره
    0.69
    Activations Density 1.602%

    No Known Activations