© 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. 6709
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and LaTeX elements indicating structure in a document

    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
     betweenstory
    -1.36
    Personensuche
    -1.13
     Roskov
    -0.96
    osoba
    -0.95
    OGND
    -0.94
     Мексичка
    -0.93
    RectangleBorder
    -0.93
    MessageOf
    -0.86
     tartalomajánló
    -0.85
    fjspx
    -0.85
    POSITIVE LOGITS
    qquad
    0.56
    or
    0.54
    ag
    0.53
    quad
    0.52
     
    0.50
    すす
    0.50
     for
    0.49
     period
    0.47
    -
    0.47
    for
    0.47
    Activations Density 0.114%

    No Known Activations