© 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. 14514
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of specific letters or digits, indicating patterns or sequences

    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
     ویکی‌پدیا
    -1.07
    GEBURTSDATUM
    -0.96
     дописавши
    -0.94
    GIH
    -0.92
    انيف
    -0.86
    NameInMap
    -0.79
    RegistryLite
    -0.79
    principalColumn
    -0.70
     nakalista
    -0.69
    featureID
    -0.67
    POSITIVE LOGITS
     therefrom
    0.49
    visející
    0.44
    "]];
    0.44
     therefor
    0.43
     مرئيه
    0.43
    mechan
    0.43
     MECHAN
    0.43
    kai
    0.42
     politically
    0.42
     Nicola
    0.42
    Activations Density 0.076%

    No Known Activations