© 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. 12-RES-MATRYOSHKA-DC
    7. 8908
    Prev
    Next
    INDEX
    Explanations

    phrases related to political entities, specifically references to republics

    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
    AsUp
    -0.90
    
    -0.82
    ########.
    -0.80
    tonode
    -0.79
    cetamol
    -0.79
    expandindo
    -0.79
     Kidman
    -0.76
    gdx
    -0.76
     ग्राहक
    -0.75
    haired
    -0.75
    POSITIVE LOGITS
     Republic
    1.42
    Republic
    1.29
     republic
    1.09
     REPUBLIC
    0.93
    republic
    0.83
     République
    0.82
     republics
    0.77
     Republik
    0.75
     Republica
    0.75
     Republics
    0.74
    Activations Density 0.008%

    No Known Activations