© 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. 20472
    Prev
    Next
    INDEX
    Explanations

    phrases related to chemical reactions and materials science

    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
     ✭✭
    -0.47
     home
    -0.46
     household
    -0.46
    gnąć
    -0.46
     nghiệp
    -0.45
    <u>
    -0.44
    pu
    -0.44
     élect
    -0.44
     Vu
    -0.43
    Демо
    -0.43
    POSITIVE LOGITS
    setVerticalGroup
    0.89
    StoryboardSegue
    0.88
    endphp
    0.82
    PerformLayout
    0.79
    fromnode
    0.78
    TagMode
    0.77
     MainAxisSize
    0.75
     TextInputType
    0.73
    ymce
    0.72
    providedIn
    0.71
    Activations Density 0.015%

    No Known Activations