© 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. 11598
    Prev
    Next
    INDEX
    Explanations

    references to the center or centroid of a spatial structure or system

    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
     Cent
    -1.09
    Cent
    -1.00
     Centre
    -0.99
     CENT
    -0.89
     Centres
    -0.87
     Center
    -0.85
     Centers
    -0.85
     CURIAM
    -0.81
    Centre
    -0.76
    Centered
    -0.76
    POSITIVE LOGITS
     center
    0.91
     middle
    0.90
     centre
    0.70
    middle
    0.62
     foreground
    0.58
     mittler
    0.53
    jsonPath
    0.53
    hoga
    0.53
    sipkan
    0.50
     mittlere
    0.50
    Activations Density 0.009%

    No Known Activations