© 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. 12320
    Prev
    Next
    INDEX
    Explanations

    the neuron’s activity related to returning to or maintaining a resting state in neural processes

    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
    AndEndTag
    -0.79
     remainder
    -0.69
    rrggbb
    -0.62
    SerializedSize
    -0.61
    MergeFrom
    -0.60
    remainder
    -0.55
     uska
    -0.54
    createTextNode
    -0.54
     beat
    -0.53
    EOUT
    -0.53
    POSITIVE LOGITS
     resting
    3.00
    resting
    2.27
     rested
    1.70
     rests
    1.17
     reposer
    0.96
     descans
    0.94
     hvil
    0.94
     reposo
    0.83
    rested
    0.75
     descansar
    0.75
    Activations Density 0.002%

    No Known Activations