© 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. 3318
    Prev
    Next
    INDEX
    Explanations

    references to the subiculum or subregion of the spinal cord

    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
     Subsid
    -0.72
     substrates
    -0.66
     Substrate
    -0.65
     substrate
    -0.60
    msub
    -0.57
     Substantial
    -0.57
     SUBST
    -0.55
    ubs
    -0.54
     subtraction
    -0.54
    ub
    -0.54
    POSITIVE LOGITS
     sub
    1.35
     CreateTagHelper
    0.86
     calendriers
    0.85
    aarrggbb
    0.84
     configureStore
    0.82
    LayoutStyle
    0.79
    Xna
    0.77
    InputBorder
    0.74
    WithIOException
    0.73
    __':
    0.72
    Activations Density 0.025%

    No Known Activations