© 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. 13881
    Prev
    Next
    INDEX
    Explanations

    specific scientific and technical terms related to experimental procedures and materials

    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
    UserScript
    -0.49
     nakalista
    -0.48
    fxml
    -0.45
    all
    -0.43
    類
    -0.39
    rob
    -0.38
    Населення
    -0.38
     =
    -0.36
    dart
    -0.36
     incontr
    -0.36
    POSITIVE LOGITS
    endforeach
    0.73
    chaun
    0.73
     Reſ
    0.69
     Савез
    0.68
    poň
    0.67
    CompilerServices
    0.65
    NUMX
    0.65
     Majefty
    0.65
    THISDAY
    0.64
     itſelf
    0.64
    Activations Density 0.430%

    No Known Activations