© 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. 17573
    Prev
    Next
    INDEX
    Explanations

    the presence of legal terminology and concepts related to the judicial process

    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
    %");
    -0.47
     remain
    -0.46
    .*;
    -0.46
     تكبرها
    -0.46
    !="")
    -0.45
    endforeach
    -0.45
    就去
    -0.45
    ')){
    -0.43
    adins
    -0.42
    त्ति
    -0.42
    POSITIVE LOGITS
     AssemblyVersion
    0.75
     sûrement
    0.68
    probably
    0.67
    ISupport
    0.66
     probably
    0.66
    typically
    0.65
     Typically
    0.64
     rarement
    0.64
     likely
    0.64
     provavelmente
    0.64
    Activations Density 0.418%

    No Known Activations