© 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. 30755
    Prev
    Next
    INDEX
    Explanations

    LaTeX math expressions and equations

    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
    adget
    -0.65
    voerd
    -0.63
     Delaney
    -0.63
    monary
    -0.61
     timeval
    -0.61
     Danilo
    -0.57
     Hoàng
    -0.57
    yip
    -0.57
    BaseAdapter
    -0.55
     Agassi
    -0.55
    POSITIVE LOGITS
     виправивши
    0.89
    ='\
    0.68
     Obec
    0.66
     présent
    0.66
    ThroughAttribute
    0.66
     AssemblyCulture
    0.66
     Elé
    0.66
     EAR
    0.65
    NOPQRST
    0.65
    zeu
    0.64
    Activations Density 0.018%

    No Known Activations