© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17464
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting actions or processes related to legal or court contexts

    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
     appelez
    -0.54
    PreferredItem
    -0.50
     wynosi
    -0.49
    ListOf
    -0.47
    toHave
    -0.46
    TagHelpers
    -0.46
     McGee
    -0.45
    場で
    -0.42
     PARSER
    -0.41
    arabe
    -0.41
    POSITIVE LOGITS
     thereby
    0.74
     dabei
    0.71
     بذلك
    0.69
     exposing
    0.67
    mités
    0.67
     daarbij
    0.67
     AssemblyCulture
    0.66
     Dabei
    0.66
    InSection
    0.65
     čím
    0.65
    Activations Density 0.035%

    No Known Activations