© 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. 5-CLT-HP
    7. 94737
    Prev
    Next
    INDEX
    Explanations

    religion and mythology

    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
    ConstraintMaker
    -0.78
    EndGlobalSection
    -0.77
     مشين
    -0.74
    TagMode
    -0.71
    LookAnd
    -0.70
     فريبيس
    -0.68
    tdessen
    -0.66
     resourceCulture
    -0.66
    RegressionTest
    -0.65
    
    -0.65
    POSITIVE LOGITS
     Goddess
    0.63
     goddesses
    0.57
     goddess
    0.57
     Deity
    0.49
    Goddess
    0.48
     Hera
    0.47
     Religions
    0.47
     Segen
    0.47
    goddess
    0.46
     Cults
    0.46
    Activations Density 0.005%

    No Known Activations