© 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. 7982
    Prev
    Next
    INDEX
    Explanations

    references to different practices or 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
    RectangleBorder
    -0.83
    ngOnInit
    -0.79
    SerializeField
    -0.74
     Ked
    -0.73
     Keats
    -0.73
    InputBorder
    -0.72
     المعرف
    -0.71
    demort
    -0.71
    OSD
    -0.70
     Metabol
    -0.69
    POSITIVE LOGITS
     practices
    1.74
     practice
    1.70
     Practices
    1.68
     Practice
    1.67
     PRACTICE
    1.66
    Practice
    1.59
    Practices
    1.57
    PRACTICE
    1.56
     practise
    1.52
    practices
    1.48
    Activations Density 0.035%

    No Known Activations