© 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. 2-RES-MATRYOSHKA-DC
    7. 4620
    Prev
    Next
    INDEX
    Explanations

    words related to religious or spiritual doctrines, beliefs, or activities

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Docket
    -0.51
     }{@
    -0.51
    WithIOException
    -0.49
    badlogic
    -0.47
    talet
    -0.47
     culturelles
    -0.47
    voj
    -0.45
     moder
    -0.45
    ;->
    -0.45
    (&:
    -0.45
    POSITIVE LOGITS
    ########.
    0.71
     Chwiliwch
    0.66
    saraba
    0.65
    AddTagHelper
    0.65
     Viro
    0.65
    IGraphics
    0.61
    ModelBuilder
    0.60
     fathoms
    0.59
    noz
    0.59
     autorytatywna
    0.59
    Activations Density 0.343%

    No Known Activations