© 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. 21268
    Prev
    Next
    INDEX
    Explanations

    repetitive sequences or patterns in text

    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
    ConstraintMaker
    -0.88
     AssemblyVersion
    -0.84
    RetentionPolicy
    -0.79
    ########.
    -0.77
    StoryboardSegue
    -0.77
    onOptions
    -0.76
    Hochspringen
    -0.73
    KommentareTeilen
    -0.73
     AssemblyProduct
    -0.72
     AspNetCore
    -0.70
    POSITIVE LOGITS
    ']")
    0.48
    zeiger
    0.47
     مشين
    0.43
    `)
    0.40
    ))]
    0.40
     living
    0.40
    ↵↵
    0.40
     Harvey
    0.40
    kolan
    0.39
    </h6>
    0.39
    Activations Density 0.003%

    No Known Activations