© 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. 3-RES-MATRYOSHKA-DC
    7. 1877
    Prev
    Next
    INDEX
    Explanations

    mentions of the brain and nervous system, especially related to damage or injury

    oai_token-act-pair · gemini-2.0-flash
    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
     Claus
    -0.54
     Burrell
    -0.54
     Boucher
    -0.54
     Molina
    -0.53
    acal
    -0.53
    vend
    -0.53
     Salter
    -0.51
     lapar
    -0.51
    basa
    -0.50
    beke
    -0.49
    POSITIVE LOGITS
     brain
    2.64
     Brain
    2.42
    Brain
    2.33
    brain
    2.28
     brains
    2.23
     BRAIN
    2.23
     Brains
    2.05
    brains
    1.89
     neuro
    1.88
     cérebro
    1.80
    Activations Density 0.683%

    No Known Activations