© 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. 0-RES-MATRYOSHKA-DC
    7. 15116
    Prev
    Next
    INDEX
    Explanations

    references to religious or biblical objects, practices, or concepts

    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
     suspect
    -0.59
    rani
    -0.58
     Rial
    -0.56
    Vain
    -0.56
    Amm
    -0.55
    ivor
    -0.54
     Duda
    -0.54
    Wy
    -0.53
    季
    -0.53
     dép
    -0.52
    POSITIVE LOGITS
     forehead
    1.47
    amus
    1.06
    atri
    0.97
     Marty
    0.90
     extrapolated
    0.82
     extrapolation
    0.81
    kloped
    0.81
    Marty
    0.79
     martyr
    0.73
     Todd
    0.70
    Activations Density 0.003%

    No Known Activations