© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20989
    Prev
    Next
    INDEX
    Explanations

    references to political entities and geographical locations, particularly related to Bangladesh

    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
    Negative Logits
    aarrggbb
    -0.64
    marvin
    -0.56
     Erm
    -0.52
    Hers
    -0.50
    ymce
    -0.50
     retire
    -0.49
     webdriver
    -0.49
     reti
    -0.48
     Carlsbad
    -0.47
    Erm
    -0.47
    POSITIVE LOGITS
     Bangladesh
    1.24
     Banglades
    1.12
    Bangladesh
    1.11
     Dhaka
    1.05
     Bengali
    1.02
    ladesh
    0.98
    AndEndTag
    0.94
     Efq
    0.88
     Kolkata
    0.85
     Chowdhury
    0.85
    Activations Density 0.032%

    No Known Activations