© 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. 22-RES-MATRYOSHKA-DC
    7. 1968
    Prev
    Next
    INDEX
    Explanations

    legal/court documents and motions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     jurisprudence
    -0.50
     filings
    -0.49
     Roskov
    -0.48
     Complaint
    -0.47
     trámites
    -0.47
    ViewFeatures
    -0.47
     pepe
    -0.45
     plainte
    -0.45
     AssemblyProduct
    -0.45
    πον
    -0.44
    POSITIVE LOGITS
    ImageContext
    0.80
     relief
    0.72
    Демографія
    0.71
    UserScript
    0.68
    ActionCreators
    0.68
    AndroidJUnit
    0.63
    mybatisplus
    0.60
    TestTools
    0.60
    ControllerAdvice
    0.57
     leave
    0.57
    Activations Density 0.787%

    No Known Activations