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

    language common in legal documents

    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.18.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.18.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
    apimachinery
    -0.59
    ImageContext
    -0.56
    Contribute
    -0.52
    LLocation
    -0.48
    GraphicsUnit
    -0.48
    unhofer
    -0.47
     Contribute
    -0.47
    mycompany
    -0.47
    >`;
    -0.46
     jLabel
    -0.46
    POSITIVE LOGITS
     appellate
    0.84
     Appellate
    0.78
     motion
    0.76
     motions
    0.75
    SBATCH
    0.72
     Motions
    0.72
     Efq
    0.71
    ellate
    0.69
     docket
    0.69
     appeal
    0.69
    Activations Density 5.821%

    No Known Activations