© 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. 8895
    Prev
    Next
    INDEX
    Explanations

    references to legal districts or court jurisdictions

    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
    nios
    -0.49
     boards
    -0.46
    xdc
    -0.44
     sẻ
    -0.42
    nisse
    -0.42
     cost
    -0.41
     hinge
    -0.41
     hinges
    -0.41
    trz
    -0.39
     board
    -0.39
    POSITIVE LOGITS
    bootstrapcdn
    0.92
    AddTagHelper
    0.81
     protoimpl
    0.79
    Архівовано
    0.76
     للمعارف
    0.70
    obacter
    0.70
     كومونز
    0.70
    Slf
    0.69
    RenderAtEndOf
    0.68
    MemoryWarning
    0.66
    Activations Density 0.002%

    No Known Activations