© 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. 6031
    Prev
    Next
    INDEX
    Explanations

    neurons in the context of discussing pilots and aviation regulations

    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
     prest
    -0.56
    affirm
    -0.56
     bus
    -0.54
    tifying
    -0.50
     air
    -0.49
     Carnegie
    -0.49
    bus
    -0.49
     Callaway
    -0.48
     updateTime
    -0.47
     sal
    -0.47
    POSITIVE LOGITS
     pilot
    3.73
     Pilot
    3.55
    Pilot
    3.36
    pilot
    3.31
     pilots
    3.20
     PILOT
    3.13
     Pilots
    2.98
     pilo
    2.59
     piloto
    2.42
     pilota
    2.39
    Activations Density 0.017%

    No Known Activations