© 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. 31890
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions related to division

    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
     تانيه
    -0.85
     kaarangay
    -0.83
    AddTagHelper
    -0.77
    GEBURTSDATUM
    -0.75
    تقاوى
    -0.75
    Biografía
    -0.71
    Архівовано
    -0.71
    Демографія
    -0.70
     utafitiHapana
    -0.70
    
    -0.69
    POSITIVE LOGITS
    setzungen
    0.52
     sintética
    0.45
     DRO
    0.44
    না
    0.44
     r
    0.44
    ymas
    0.44
     ها
    0.44
    loc
    0.43
    мови
    0.43
    DRO
    0.43
    Activations Density 0.010%

    No Known Activations