© 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. 22953
    Prev
    Next
    INDEX
    Explanations

    legal terms and references to plaintiffs and defendants in court cases

    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
     sumpay
    -0.73
     beginnetje
    -0.68
    astify
    -0.60
     anhydrous
    -0.58
    GEBURTSDATUM
    -0.58
    celain
    -0.58
    pertise
    -0.58
    Enllaces
    -0.57
    EndGlobalSection
    -0.57
    IndentedString
    -0.57
    POSITIVE LOGITS
    Lugares
    0.50
    TagHelper
    0.48
    Rhestr
    0.48
    PreferredItem
    0.48
     jScrollPane
    0.45
    )];
    0.44
    tachment
    0.42
    )))));
    0.42
    Cabe
    0.41
    reat
    0.41
    Activations Density 0.758%

    No Known Activations