© 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. 25086
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structures, particularly related to database and XML operations

    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
     Meksiku
    -0.78
    AxisAlignment
    -0.63
    AddTagHelper
    -0.62
    ⓧ
    -0.61
    uitton
    -0.57
    phemy
    -0.53
    etheless
    -0.53
    schemas
    -0.52
     cherchés
    -0.52
    hésite
    -0.52
    POSITIVE LOGITS
     الحره
    0.69
    ########.
    0.65
    UnusedPrivate
    0.57
     propOrder
    0.56
    GetEnumerator
    0.52
    enterOuterAlt
    0.50
    findById
    0.49
     препратки
    0.49
    resenta
    0.48
    IsContent
    0.47
    Activations Density 0.020%

    No Known Activations