© 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. 17330
    Prev
    Next
    INDEX
    Explanations

    terms related to crashes and accidents

    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
    EDEFAULT
    -0.77
    actionBar
    -0.72
     kelle
    -0.71
    ểm
    -0.70
     JMenuItem
    -0.70
    ellas
    -0.69
     actionBar
    -0.69
    */
    -0.68
     himo
    -0.67
     Barb
    -0.66
    POSITIVE LOGITS
     crash
    1.45
     crashes
    1.37
     crashed
    1.37
     Cras
    1.30
     Crash
    1.23
    Crash
    1.20
    crash
    1.18
     cras
    1.13
     crashing
    1.08
    cras
    0.93
    Activations Density 0.004%

    No Known Activations