© 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. 3143
    Prev
    Next
    INDEX
    Explanations

    references to countries, especially emphasizing developing regions and their nutritional and economic issues

    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
     company
    -0.59
    イズ
    -0.52
     team
    -0.50
     gang
    -0.48
    strar
    -0.48
    SearchResults
    -0.47
     Company
    -0.47
    cokinetics
    -0.46
     charges
    -0.45
    ALLES
    -0.45
    POSITIVE LOGITS
     countries
    1.60
     cities
    1.58
     societies
    1.55
     communities
    1.48
     governments
    1.45
     universities
    1.41
     churches
    1.40
    Countries
    1.37
     companies
    1.36
     Societies
    1.36
    Activations Density 0.610%

    No Known Activations