© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 449
    Prev
    Next
    INDEX
    Explanations

    references to government entities and legal institutions in the United States

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    elemField
    -0.73
     Calli
    -0.71
    enumi
    -0.70
     EDR
    -0.68
     "..\..\..\
    -0.68
    zeich
    -0.67
     councillors
    -0.66
     calligraphy
    -0.66
     Caledonia
    -0.66
    })));
    -0.65
    POSITIVE LOGITS
     States
    1.09
     US
    1.08
     USA
    1.03
     United
    0.99
     STATES
    0.98
     Federal
    0.91
    United
    0.91
    States
    0.91
    US
    0.90
     UNITED
    0.85
    Activations Density 0.946%

    No Known Activations