© 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. 11813
    Prev
    Next
    INDEX
    Explanations

    legal terms and notations associated with court documents and opinions

    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
     themſelves
    -0.71
     myſelf
    -0.65
     himſelf
    -0.63
     deſt
    -0.63
     aveug
    -0.60
    Fußball
    -0.59
    Przypisy
    -0.59
     Pagina
    -0.58
     becauſe
    -0.58
     Euph
    -0.57
    POSITIVE LOGITS
     AssemblyCulture
    0.89
    CloseOperation
    0.72
    ChildScrollView
    0.72
    PreferredItem
    0.69
    MemoryWarning
    0.69
    tagext
    0.68
     ExecuteAsync
    0.66
    URLException
    0.65
     /
    0.65
    ContentLoaded
    0.63
    Activations Density 0.001%

    No Known Activations