© 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. 31379
    Prev
    Next
    INDEX
    Explanations

    instances and phrases related to the presentation of data or figures

    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
     muualla
    -0.74
     StatelessWidget
    -0.74
     StatefulWidget
    -0.74
    onAttach
    -0.74
    rachtet
    -0.73
     termica
    -0.70
    zęd
    -0.68
     ArrayAdapter
    -0.65
     виправивши
    -0.64
     nationaux
    -0.64
    POSITIVE LOGITS
     Vork
    0.52
    archiviato
    0.52
     كومونز
    0.50
     betweenstory
    0.47
     gro
    0.46
    fromCharCode
    0.46
    cibility
    0.45
    ÈME
    0.45
     de
    0.44
    azu
    0.43
    Activations Density 0.170%

    No Known Activations