© 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. 12791
    Prev
    Next
    INDEX
    Explanations

    specific Romanian words or names, particularly those relating to people or entities

    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
     cherchés
    -0.92
    ValueStyle
    -0.87
    انيف
    -0.85
     picioare
    -0.77
     maș
    -0.73
     >=",
    -0.71
    LookAnd
    -0.71
    enumii
    -0.71
     HasFactory
    -0.71
    riwal
    -0.71
    POSITIVE LOGITS
     Romanian
    0.86
     Romania
    0.79
    Romania
    0.76
    änien
    0.75
     Bucharest
    0.69
     թվական
    0.62
     Radu
    0.59
     Dacia
    0.52
     Ghe
    0.50
     Moldova
    0.50
    Activations Density 0.043%

    No Known Activations