© 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. 14027
    Prev
    Next
    INDEX
    Explanations

    words pertaining to legal concepts and terminology

    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
    fjspx
    -1.01
    SBATCH
    -0.82
     Ombudsman
    -0.81
     broche
    -0.75
     MIB
    -0.73
    ">—
    -0.73
     Shank
    -0.73
    MIB
    -0.73
    úde
    -0.71
     gustó
    -0.70
    POSITIVE LOGITS
     Legal
    0.90
     LEGAL
    0.85
    Legal
    0.82
     Gleaner
    0.77
     legal
    0.76
    legal
    0.74
    LEGAL
    0.74
     surgical
    0.72
    合衆
    0.70
     Cæsar
    0.68
    Activations Density 0.009%

    No Known Activations