© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12016
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of cults, particularly in the context of religious, secret, or esoteric groups

    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
    Expedia
    -0.58
    CppCodeGen
    -0.56
     للاسماء
    -0.56
    ())->
    -0.55
    utin
    -0.54
    potranspiration
    -0.54
     hóa
    -0.51
    凝土
    -0.50
    PreferredItem
    -0.50
    ectoria
    -0.49
    POSITIVE LOGITS
     cult
    3.36
    cult
    2.92
    Cult
    2.72
     Cult
    2.67
     cults
    2.14
     culto
    1.56
     culte
    1.48
     Cults
    1.40
     culti
    1.39
     CULT
    1.35
    Activations Density 0.001%

    No Known Activations