© 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. 9899
    Prev
    Next
    INDEX
    Explanations

    numerical measurements related to dosages and concentrations

    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
    0
    -0.57
     met
    -0.53
    endswith
    -0.52
    ών
    -0.52
    startswith
    -0.50
    ke
    -0.49
     broad
    -0.47
     Tw
    -0.47
     two
    -0.47
    .
    -0.47
    POSITIVE LOGITS
     Мексичка
    0.87
     Meksiku
    0.82
    :✨
    0.81
     beginnetje
    0.80
    tamment
    0.77
    原始内容存档于
    0.76
     ویکی‌آمباردا
    0.76
     '\\;'
    0.76
     surla
    0.76
    etcode
    0.74
    Activations Density 0.028%

    No Known Activations