© 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. 27038
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mechanical structures and components

    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
    XmlIgnore
    -0.61
     poveznice
    -0.43
    itate
    -0.42
    startY
    -0.42
    SpringRunner
    -0.42
    oje
    -0.42
    utilisons
    -0.41
    ffine
    -0.41
     Theorem
    -0.41
     projecting
    -0.41
    POSITIVE LOGITS
     InputDecoration
    0.66
    ModelAdmin
    0.62
    CloseOperation
    0.60
     boîtier
    0.60
    invokeLater
    0.60
    脚注の使い方
    0.59
     carcasa
    0.59
     frame
    0.58
     Rahmen
    0.58
     Frames
    0.58
    Activations Density 0.069%

    No Known Activations