© 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. 4971
    Prev
    Next
    INDEX
    Explanations

    references to the spirit or essence of an idea or feeling

    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
    "]);
    -0.69
    ]){
    -0.67
     AssemblyTitle
    -0.65
     STC
    -0.65
    )";
    -0.65
    gdx
    -0.65
    ")){
    -0.65
     }}$}
    -0.65
    "]
    -0.64
    imedes
    -0.64
    POSITIVE LOGITS
     spirit
    3.77
    spirit
    3.55
     Spirit
    3.39
    Spirit
    3.27
     SPIRIT
    2.95
     spirits
    2.69
     espíritu
    2.47
     Spirits
    2.41
     espírito
    2.23
     spirito
    2.22
    Activations Density 0.012%

    No Known Activations