© 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. 15942
    Prev
    Next
    INDEX
    Explanations

    escape characters and specific formatting syntax

    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
    نجليزية
    -0.43
     replacing
    -0.40
    Col
    -0.40
    ymal
    -0.40
     Mengen
    -0.39
    
    -0.39
    ydı
    -0.38
    tze
    -0.38
    geladen
    -0.38
    羅斯
    -0.38
    POSITIVE LOGITS
    tagHelperRunner
    1.07
    XmlAccessorType
    0.91
    migrationBuilder
    0.87
    ;->
    0.86
    ⓧ
    0.81
    bootstrapcdn
    0.79
    Autoritní
    0.78
     كومونز
    0.76
     مرئيه
    0.75
    Hozzáférés
    0.75
    Activations Density 0.002%

    No Known Activations