© 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. 25878
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to limits 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
     limited
    -0.67
     restre
    -0.66
     byd
    -0.63
    Stencil
    -0.63
    Karla
    -0.63
    şekkür
    -0.62
    limited
    -0.62
     intStringLen
    -0.59
    ed
    -0.59
     terbatas
    -0.58
    POSITIVE LOGITS
    WebVitals
    0.83
     Findlay
    0.81
    entin
    0.80
    bootstrapcdn
    0.79
    XCT
    0.75
     /\.
    0.75
     Guil
    0.74
    ibatis
    0.74
    !*\
    0.74
    PENT
    0.73
    Activations Density 0.017%

    No Known Activations