© 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. 2-RES-MATRYOSHKA-DC
    7. 4083
    Prev
    Next
    INDEX
    Explanations

    references to the human soul

    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
    NameInMap
    -0.61
     zwierzę
    -0.61
    ppled
    -0.60
     liné
    -0.60
    webElementXpaths
    -0.59
    MessageTagHelper
    -0.59
    richTextPanel
    -0.58
    expandindo
    -0.58
     Roskov
    -0.57
     gouvernements
    -0.57
    POSITIVE LOGITS
     soul
    3.73
    soul
    3.28
     Soul
    3.22
     souls
    3.08
    Soul
    3.03
     SOUL
    2.89
     Souls
    2.63
    Souls
    2.33
     âme
    2.06
    灵魂
    1.91
    Activations Density 0.004%

    No Known Activations