© 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. 9531
    Prev
    Next
    INDEX
    Explanations

    corporate and legal names, particularly related to maritime law and organizations

    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
     Personal
    -0.58
    Personal
    -0.50
     personal
    -0.49
     Federal
    -0.42
     Leicht
    -0.40
    :
    -0.40
     district
    -0.39
    personal
    -0.38
    巷
    -0.38
     Co
    -0.37
    POSITIVE LOGITS
    EndInit
    0.90
     FetchType
    0.81
    tagHelperRunner
    0.76
     EClass
    0.75
    CppMethod
    0.74
     RequestMethod
    0.71
     tslint
    0.70
    LayoutPanel
    0.69
    TagMode
    0.68
     calendriers
    0.68
    Activations Density 0.047%

    No Known Activations