© 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. 20294
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to economic factors

    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
    ollectionView
    -0.53
    argout
    -0.53
    ēju
    -0.52
     Morten
    -0.50
     références
    -0.47
    ITECH
    -0.46
     tuya
    -0.45
     bibliothèque
    -0.45
    vių
    -0.45
    romat
    -0.45
    POSITIVE LOGITS
     propOrder
    0.85
    Хьажоргаш
    0.74
    titleMargin
    0.69
     himo
    0.69
     Italijani
    0.68
    oredCriteria
    0.68
    parsedMessage
    0.65
    +#+#
    0.64
    PhysRev
    0.62
    providedIn
    0.61
    Activations Density 0.048%

    No Known Activations