© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43010
    Prev
    Next
    INDEX
    Explanations

    capitalism, greed, and shame

    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
     capitalism
    -1.08
     individualism
    -0.94
    LookAnd
    -0.92
     Capitalism
    -0.91
     shame
    -0.90
    DockStyle
    -0.89
    Trading
    -0.87
    berdayakan
    -0.87
    WriteTagHelper
    -0.87
     trading
    -0.86
    POSITIVE LOGITS
    ers
    0.59
     bl
    0.50
    iness
    0.49
    ER
    0.47
    ys
    0.47
     A
    0.46
    ens
    0.46
    ings
    0.46
    um
    0.46
    ily
    0.45
    Activations Density 0.043%

    No Known Activations