© 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. 10568
    Prev
    Next
    INDEX
    Explanations

    structured data or formatting patterns in numerical or categorical information

    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
    CppMethod
    -1.02
    ighed
    -0.97
    IZABETH
    -0.94
    ‍♀️
    -0.93
     Trang
    -0.92
    resultCode
    -0.92
     propOrder
    -0.90
    Manbalar
    -0.90
     &___
    -0.90
     nahilalakip
    -0.89
    POSITIVE LOGITS
    er
    1.58
    ing
    1.21
                  
    1.08
    en
    0.97
    erent
    0.95
     Beecher
    0.92
    ER
    0.82
    ة
    0.82
    ená
    0.80
     ecco
    0.79
    Activations Density 0.036%

    No Known Activations