© 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. 29789
    Prev
    Next
    INDEX
    Explanations

    mentions of death and dying

    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
    kills
    -0.50
    funeral
    -0.49
     killed
    -0.47
     death
    -0.47
     deaths
    -0.47
    inalg
    -0.47
     killing
    -0.47
    Killed
    -0.46
     kill
    -0.44
     euth
    -0.44
    POSITIVE LOGITS
     للمعارف
    0.92
    djangoproject
    0.90
    lccn
    0.84
    ValueStyle
    0.84
     snippetHide
    0.82
     Roskov
    0.79
     unknownFields
    0.75
    MemoryWarning
    0.75
    jednoc
    0.73
    lemény
    0.72
    Activations Density 0.012%

    No Known Activations