© 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. 18640
    Prev
    Next
    INDEX
    Explanations

    instances of string patterns and formatting syntax in code or markup

    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
     vorg
    -0.44
    还好
    -0.43
     désolés
    -0.43
     beina
    -0.41
    ItemBackground
    -0.41
    point
    -0.40
    intrag
    -0.40
     off
    -0.39
    َّ
    -0.38
    히
    -0.38
    POSITIVE LOGITS
    MigrationBuilder
    1.05
    ]")]
    0.80
    tvguidetime
    0.75
    expandindo
    0.75
    ')));
    0.74
    ))).
    0.73
     Wikimedijinoj
    0.73
     defaultstate
    0.73
     مرئيه
    0.72
    SpringRunner
    0.72
    Activations Density 0.034%

    No Known Activations