© 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. 14912
    Prev
    Next
    INDEX
    Explanations

    the presence of specific scientific terminology related to research and study methodologies

    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
     propOrder
    -0.76
    AutoresizingMask
    -0.69
     StatelessWidget
    -0.65
     setTotal
    -0.62
    ########.
    -0.59
     setuptools
    -0.58
    \{\\
    -0.57
     volna
    -0.57
    bonucleic
    -0.56
    Revenir
    -0.56
    POSITIVE LOGITS
     research
    0.62
    发表于
    0.57
     researches
    0.52
     lab
    0.52
     exploring
    0.50
     investigate
    0.49
     исследования
    0.49
     Lab
    0.48
     иссле
    0.47
     investigating
    0.47
    Activations Density 0.169%

    No Known Activations