© 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. 6753
    Prev
    Next
    INDEX
    Explanations

    references to specific countries, notably Haiti and Honduras

    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
     Spain
    -0.98
     France
    -0.98
    France
    -0.93
     Italy
    -0.93
    Spain
    -0.93
     Germany
    -0.87
    Germany
    -0.87
    Italy
    -0.86
     Europe
    -0.84
     france
    -0.82
    POSITIVE LOGITS
     Belize
    1.24
     Guyana
    1.18
     Malawi
    1.17
    Haiti
    1.13
     Zimbabwe
    1.12
     Kosovo
    1.10
     Liberia
    1.10
     Uganda
    1.09
     Haiti
    1.08
     Rwanda
    1.08
    Activations Density 0.233%

    No Known Activations