© 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. 280
    Prev
    Next
    INDEX
    Explanations

    whether the context involves electrical concepts or control schemes related to Direct Current (DC) and field-oriented control (FOC)

    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
     defaultstate
    -0.69
     '\\;'
    -0.69
    makeConstraints
    -0.67
    reactstrap
    -0.67
     FORECAST
    -0.67
    دانشنامهٔ
    -0.67
     FontWeight
    -0.60
     REACTOR
    -0.57
     RECRE
    -0.56
    awtextra
    -0.56
    POSITIVE LOGITS
     getID
    0.81
     TX
    0.78
    GEBURTSDATUM
    0.75
    HT
    0.73
     OMG
    0.73
     FL
    0.72
     EC
    0.72
    getID
    0.72
    ORPG
    0.72
     málaga
    0.71
    Activations Density 4.171%

    No Known Activations