© 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. 11898
    Prev
    Next
    INDEX
    Explanations

    legal terms, specifically those related to judicial opinions and dissenting remarks

    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
    StoryboardSegue
    -0.85
    abestanden
    -0.79
    tvguidetime
    -0.76
    IntoConstraints
    -0.72
    ChildScrollView
    -0.71
    Personendaten
    -0.69
    KommentareTeilen
    -0.68
    MLLoader
    -0.67
    TintMode
    -0.67
    igshid
    -0.65
    POSITIVE LOGITS
     part
    0.62
     personal
    0.47
    दार
    0.47
    частли
    0.47
    part
    0.46
    ticoli
    0.44
     gio
    0.43
    ouche
    0.43
     للمعارف
    0.43
     block
    0.43
    Activations Density 0.030%

    No Known Activations