© 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. 12228
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or patterns in datasets

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -1.23
    findpost
    -1.18
     Мексичка
    -1.13
     الرياضيه
    -1.04
    webElementXpaths
    -0.99
    Personensuche
    -0.96
     дописавши
    -0.93
     unknownFields
    -0.93
    ConstraintMaker
    -0.92
     متعلقه
    -0.92
    POSITIVE LOGITS
     accol
    0.47
    ின
    0.45
    ust
    0.43
    ?
    0.42
    mockito
    0.42
    tical
    0.41
    тельству
    0.40
     venezolano
    0.40
    かれた
    0.39
     next
    0.38
    Activations Density 0.042%

    No Known Activations