© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9267
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and statements made in a courtroom context

    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
    Negative Logits
    WithIOException
    -0.58
    IGraphics
    -0.55
    BagConstraints
    -0.55
     
    -0.55
    ">—
    -0.54
    UniformLocation
    -0.53
    ,:),
    -0.52
    ManyToMany
    -0.51
     inalámbrico
    -0.51
    TintMode
    -0.48
    POSITIVE LOGITS
    egg
    0.52
    istern
    0.48
     recul
    0.48
    ricist
    0.47
    Datuak
    0.47
    veling
    0.47
    GTCX
    0.46
     egg
    0.46
     goederen
    0.46
    bietern
    0.45
    Activations Density 0.226%

    No Known Activations