© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4475
    Prev
    Next
    INDEX
    Explanations

    references to United States Courts and legal 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
     bajo
    -0.46
    <eos>
    -0.41
    Kjelder
    -0.40
    報導
    -0.39
    KeyId
    -0.38
    toContain
    -0.38
    踐
    -0.38
    dor
    -0.38
    yntaxException
    -0.38
     referenties
    -0.38
    POSITIVE LOGITS
    RectangleBorder
    0.87
    PerformLayout
    0.84
    oredCriteria
    0.80
     للاسماء
    0.77
     transfieras
    0.73
    JspWriter
    0.73
    AnimationsModule
    0.71
    transQ
    0.70
     وتسجيلات
    0.69
    ValueStyle
    0.68
    Activations Density 0.043%

    No Known Activations