© 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. 94757
    Prev
    Next
    INDEX
    Explanations

    religious themes

    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
    TestingModule
    -0.53
     theory
    -0.52
     extinction
    -0.52
     Universe
    -0.48
     illustrator
    -0.46
     universe
    -0.45
    othed
    -0.45
    especie
    -0.45
     Turf
    -0.45
     concepts
    -0.44
    POSITIVE LOGITS
    хьтан
    0.79
     enfans
    0.72
     altrimenti
    0.70
     mauvaises
    0.69
     noDo
    0.68
     fermés
    0.68
    Autoritní
    0.67
     étoient
    0.66
     étoit
    0.66
     ouverts
    0.65
    Activations Density 0.013%

    No Known Activations