© 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. 18-RES-MATRYOSHKA-DC
    7. 1547
    Prev
    Next
    INDEX
    Explanations

    technical documents explaining the key components of a system.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    出版年
    -0.90
    Tikang
    -0.77
     referrerpolicy
    -0.61
    たまた
    -0.60
    enderror
    -0.60
    IVEREF
    -0.59
     AssemblyTitle
    -0.58
    saraba
    -0.57
    tangentMode
    -0.57
    setupUi
    -0.56
    POSITIVE LOGITS
     consists
    2.64
     consisting
    2.52
     consisted
    2.41
     consist
    2.34
     comprised
    2.33
     composed
    2.31
     terdiri
    2.16
     comprises
    2.09
     comprising
    2.03
    composed
    2.02
    Activations Density 1.598%

    No Known Activations