© 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. 22486
    Prev
    Next
    INDEX
    Explanations

    references to Saudi Arabia and related geographical terms

    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
     Livingston
    -0.58
    EqualsAnd
    -0.52
     Biss
    -0.52
     Berlin
    -0.52
     "
    -0.51
     sẻ
    -0.51
     fleas
    -0.50
     ठ
    -0.50
    的存在
    -0.50
     appart
    -0.50
    POSITIVE LOGITS
     Saudi
    1.88
    Saudi
    1.84
     Arabia
    1.45
     Saud
    1.34
     Arabian
    1.18
     Sau
    1.15
     السعودية
    1.14
     سعود
    1.13
     Riyadh
    1.13
    Sau
    1.11
    Activations Density 0.003%

    No Known Activations