© 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. 10710
    Prev
    Next
    INDEX
    Explanations

    mathematical labels and concepts related to equations and definitions

    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
    StoryboardSegue
    -0.72
    httphttps
    -0.69
     &___
    -0.66
     astore
    -0.63
     itſelf
    -0.62
     poffible
    -0.62
    Toponymie
    -0.61
     neceffary
    -0.60
     magnétique
    -0.58
     myſelf
    -0.57
    POSITIVE LOGITS
     CreateTagHelper
    0.51
    disposing
    0.50
    enumii
    0.49
    setVerticalGroup
    0.49
    andExpect
    0.48
    ModelBuilder
    0.46
    SourceChecksum
    0.46
     TextAppearance
    0.45
    dette
    0.45
     ago
    0.43
    Activations Density 0.004%

    No Known Activations