© 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. 1769
    Prev
    Next
    INDEX
    Explanations

    peaceful

    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
     Faithful
    -0.69
     fidèles
    -0.68
     fidèle
    -0.57
    fashion
    -0.56
     fashion
    -0.54
    peaceful
    -0.54
     locaux
    -0.52
     Fashion
    -0.52
     peaceful
    -0.52
     nationaux
    -0.50
    POSITIVE LOGITS
    ised
    0.83
    ization
    0.82
    izations
    0.82
    ized
    0.78
    izing
    0.74
    izes
    0.72
    isation
    0.71
    ities
    0.66
    ists
    0.65
    ising
    0.64
    Activations Density 1.372%

    No Known Activations