© 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. 0-CLT-HP
    7. 41452
    Prev
    Next
    INDEX
    Explanations

    groups of people

    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
     itſelf
    -1.18
     victims
    -1.13
     sufferers
    -1.09
     ſche
    -1.07
     posterity
    -1.02
     martyrs
    -1.00
     Numerade
    -0.99
     survivors
    -0.99
     captives
    -0.96
     losers
    -0.96
    POSITIVE LOGITS
     who
    0.88
    hips
    0.78
     in
    0.77
    ’
    0.75
     and
    0.72
    '
    0.69
     of
    0.68
     from
    0.66
     living
    0.65
     working
    0.63
    Activations Density 0.159%

    No Known Activations