© 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. 12577
    Prev
    Next
    INDEX
    Explanations

    mentions of Italy and Italian culture

    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
     Jackman
    -0.72
    en
    -0.67
    <blockquote>
    -0.66
    shields
    -0.65
     Schrader
    -0.65
    proba
    -0.62
     X
    -0.62
     Praga
    -0.61
     Rukh
    -0.61
    ccf
    -0.61
    POSITIVE LOGITS
     Italy
    1.05
     Itali
    1.04
     Italians
    0.99
    Italie
    0.97
     italy
    0.96
     ITAL
    0.96
    Italy
    0.94
     ITALY
    0.94
     Italian
    0.93
     ital
    0.93
    Activations Density 0.004%

    No Known Activations