© 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. 40369
    Prev
    Next
    INDEX
    Explanations

    liberalism

    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
     liberal
    -0.94
     Establishment
    -0.85
     beating
    -0.83
     liberals
    -0.81
     beaten
    -0.78
     establishment
    -0.72
     Liberal
    -0.71
    liberal
    -0.69
     beat
    -0.67
    beat
    -0.66
    POSITIVE LOGITS
     CreateTagHelper
    0.88
    GraphicsUnit
    0.50
    oplan
    0.49
    ưởng
    0.49
    libft
    0.48
    noah
    0.48
     newBuilder
    0.48
     obstante
    0.47
    parsedMessage
    0.47
    êm
    0.46
    Activations Density 0.994%

    No Known Activations