© 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. 6184
    Prev
    Next
    INDEX
    Explanations

    phrases indicating authorship or citation of research findings

    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
     Meksiku
    -0.77
     ویکی‌پدیا
    -0.75
    rungsseite
    -0.69
    őle
    -0.64
    =$?
    -0.63
     autorytatywna
    -0.61
    HideFlags
    -0.61
     traseiro
    -0.60
     EnglishChoose
    -0.59
    zarchiwizowane
    -0.59
    POSITIVE LOGITS
    \{\\
    0.59
    templateUrl
    0.51
     useEffect
    0.50
     tän
    0.47
     MonoBehaviour
    0.47
    addPreferredGap
    0.45
    feira
    0.44
    一出
    0.42
    şehir
    0.42
    iotensin
    0.42
    Activations Density 0.179%

    No Known Activations