© 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. 0-RES-MATRYOSHKA-DC
    7. 13522
    Prev
    Next
    INDEX
    Explanations

    references to religious or spiritual purification actions

    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
     '\\;'
    -0.66
     extr
    -0.61
     censiti
    -0.61
     архивлан
    -0.58
    cloudf
    -0.56
    ográficas
    -0.56
    protos
    -0.56
    extr
    -0.55
    orianCalendar
    -0.55
     raiſ
    -0.55
    POSITIVE LOGITS
    Citations
    1.14
    Toma
    0.78
     Mus
    0.74
    chant
    0.72
     gând
    0.72
     nahilalakip
    0.72
    acs
    0.71
    UnitTesting
    0.71
     coffin
    0.67
    scsi
    0.66
    Activations Density 0.027%

    No Known Activations