© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 256
    Prev
    Next
    INDEX
    Explanations

    geographic place names and their relationships to other ones.

    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
     Etrus
    -0.79
     Maori
    -0.77
     Florentine
    -0.73
     Athenian
    -0.70
     Khmer
    -0.67
     Haitian
    -0.66
     Assyrian
    -0.66
     Māori
    -0.65
     Macedonian
    -0.64
     Siamese
    -0.62
    POSITIVE LOGITS
     California
    1.20
     South
    1.15
     Canada
    1.09
     Texas
    1.06
     Australia
    1.05
     southern
    1.05
     North
    1.05
     New
    1.05
     Florida
    0.99
     northern
    0.98
    Activations Density 2.596%

    No Known Activations