© 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. 30024
    Prev
    Next
    INDEX
    Explanations

    entities involved in death or significant life events

    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
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.56
     setObject
    -0.54
    parsedMessage
    -0.52
    󠁢
    -0.52
    apimachinery
    -0.51
    ANDE
    -0.50
     jTextField
    -0.50
    URLException
    -0.49
     QtCore
    -0.49
    ioka
    -0.49
    POSITIVE LOGITS
     تانيه
    0.93
     متعلقه
    0.90
    帖最后由
    0.83
    expandindo
    0.76
    
    0.73
     للمعارف
    0.71
     MainAxisSize
    0.68
    ⓧ
    0.66
    SpringBootTest
    0.62
    itename
    0.61
    Activations Density 0.147%

    No Known Activations