© 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. 9280
    Prev
    Next
    INDEX
    Explanations

    sequences of ellipses or continuations in mathematical contexts

    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
    monix
    -0.81
     Lombard
    -0.75
    
    -0.73
     Huxley
    -0.71
    displaymath
    -0.68
    jsdelivr
    -0.68
     Xamarin
    -0.67
    pitre
    -0.67
     Bourne
    -0.67
     Datuk
    -0.66
    POSITIVE LOGITS
    dots
    1.04
     Dots
    0.96
    Dots
    0.85
     spol
    0.74
     dots
    0.73
     Spots
    0.71
     SEÑ
    0.71
     Brend
    0.70
    flink
    0.69
     Kela
    0.69
    Activations Density 0.004%

    No Known Activations