© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4801
    Prev
    Next
    INDEX
    Explanations

    references to the executive branch

    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
     bulky
    -0.57
    IContainer
    -0.57
    墟
    -0.54
    隊
    -0.52
     phường
    -0.51
     Madre
    -0.50
    λω
    -0.50
    pektor
    -0.49
     carico
    -0.49
    Fest
    -0.48
    POSITIVE LOGITS
     executive
    3.72
     Executive
    3.59
    Executive
    3.45
    executive
    3.36
     EXECUTIVE
    3.27
    EXECUTIVE
    3.02
     Executives
    2.55
     ejecutivo
    2.50
     executives
    2.38
     exec
    2.36
    Activations Density 0.008%

    No Known Activations