© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3346
    Prev
    Next
    INDEX
    Explanations

    phrases that involve trade and moving goods

    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
    Negative Logits
    免許
    -0.46
    pen
    -0.45
    󠁢
    -0.43
    cost
    -0.43
    lk
    -0.42
    pensione
    -0.42
    compile
    -0.42
     SwiftUI
    -0.42
    atação
    -0.41
    url
    -0.41
    POSITIVE LOGITS
     cargo
    1.21
     goods
    1.19
     cargoes
    1.08
     Cargo
    1.06
    Cargo
    1.06
     contraband
    1.05
    cargo
    1.03
     commodities
    0.96
    goods
    0.96
     luggage
    0.93
    Activations Density 1.623%

    No Known Activations