© 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. 0-RES-MATRYOSHKA-DC
    7. 12085
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations within Central America, particularly countries and regions involved in reporting or events

    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
    WriteBarrier
    -0.82
    ISupport
    -0.76
    Hawaii
    -0.69
     Oahu
    -0.69
     PSP
    -0.68
    OGND
    -0.68
    pasti
    -0.68
     Hawaii
    -0.67
    ValueStyle
    -0.66
    raborty
    -0.65
    POSITIVE LOGITS
     Nicaragua
    1.36
     Rwanda
    1.34
     Rwand
    1.30
     Guatemala
    1.28
    Nicaragua
    1.17
     Burundi
    1.13
    Guatemala
    1.09
     Cambodia
    1.08
    Bolivia
    1.07
    Rwanda
    1.07
    Activations Density 0.009%

    No Known Activations