© 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. 22-RES-MATRYOSHKA-DC
    7. 1877
    Prev
    Next
    INDEX
    Explanations

    lists of countries or locations

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.62
     Krieges
    -0.59
     Jahrhundert
    -0.51
     السياسية
    -0.51
     quận
    -0.50
     distrik
    -0.50
    IGraphics
    -0.49
     mieście
    -0.49
     wojny
    -0.48
    Насе
    -0.48
    POSITIVE LOGITS
     UK
    1.10
     Japanese
    1.03
     Netherlands
    0.99
     British
    0.98
     German
    0.96
     Australian
    0.96
     Swedish
    0.96
     Japan
    0.95
     Czech
    0.95
     Canadian
    0.93
    Activations Density 0.822%

    No Known Activations