© 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. 22-RES-MATRYOSHKA-DC
    7. 3166
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of processes within a field (possibly technology or government)

    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.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     pleaſure
    -0.86
     ſmall
    -0.81
     quæ
    -0.76
     greateſt
    -0.76
     himſelf
    -0.74
     uſ
    -0.73
     purpoſe
    -0.70
     ſeveral
    -0.70
     beſt
    -0.70
    المكان
    -0.70
    POSITIVE LOGITS
     viz
    0.76
    doh
    0.60
     Incidentally
    0.59
    FWIW
    0.50
    viz
    0.49
     \&
    0.45
     Legislature
    0.45
     quaint
    0.44
     Indian
    0.43
     foray
    0.43
    Activations Density 0.152%

    No Known Activations