© 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. 1-RES-MATRYOSHKA-DC
    7. 892
    Prev
    Next
    INDEX
    Explanations

    references to biochemical processes involving inhibition

    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
    celes
    -0.56
     Kader
    -0.56
     crisis
    -0.54
     poor
    -0.53
     Euer
    -0.52
    ConstraintMaker
    -0.52
     ngu
    -0.50
    স্
    -0.49
    Derbyniad
    -0.49
     homeless
    -0.49
    POSITIVE LOGITS
     inhibition
    3.53
     Inhibition
    3.33
     inhibited
    2.92
     inhibit
    2.91
     Inhibit
    2.83
     inhibiting
    2.81
     inhibitor
    2.77
     inhibitors
    2.75
     inhibitory
    2.66
    hibition
    2.55
    Activations Density 0.299%

    No Known Activations