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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96881
    Prev
    Next
    INDEX
    Explanations

    Describing people's characteristics

    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
    ValueGeneration
    -0.56
    verture
    -0.50
     whiteColor
    -0.49
     mostrarán
    -0.49
    yness
    -0.48
     gmina
    -0.48
    ksom
    -0.48
    ussis
    -0.47
     accompag
    -0.46
    textTheme
    -0.46
    POSITIVE LOGITS
     agents
    0.79
     believers
    0.69
     traders
    0.69
     climbers
    0.69
     bullies
    0.68
     beings
    0.68
     brokers
    0.67
    agents
    0.66
     players
    0.65
     settlers
    0.65
    Activations Density 0.001%

    No Known Activations