© 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. 27882
    Prev
    Next
    INDEX
    Explanations

    specific terminology related to chemical processes and reactions involving transition metals

    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
     '\\;'
    -1.14
     createState
    -0.96
    AndEndTag
    -0.95
     تضيفلها
    -0.94
     initComponents
    -0.94
    AddHtmlAttribute
    -0.91
    tagHelperRunner
    -0.89
    ChildScrollView
    -0.81
     AssemblyCulture
    -0.81
     transférez
    -0.77
    POSITIVE LOGITS
     asemenea
    0.51
    Cyfeiriadau
    0.49
    <strong>
    0.46
     laiton
    0.46
    ➽
    0.45
     “
    0.45
     sī
    0.45
     Preston
    0.44
    <h5>
    0.44
    лай
    0.43
    Activations Density 0.212%

    No Known Activations