© 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. 22-RES-MATRYOSHKA-DC
    7. 2126
    Prev
    Next
    INDEX
    Explanations

    uses of the word "filed" in a legal sense along with related words like "petition" or "complaint"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    +#+#
    -0.77
     file
    -0.67
     Reinhard
    -0.66
    file
    -0.65
     Walkover
    -0.63
    __":
    -0.60
    __':
    -0.59
    tonsoft
    -0.59
    reton
    -0.59
    File
    -0.58
    POSITIVE LOGITS
     suit
    0.57
     taxes
    0.56
     Taxes
    0.52
    adaptiveStyles
    0.50
    Przypisy
    0.49
     Narod
    0.48
     Fle
    0.48
     police
    0.47
    lccn
    0.46
     cabinets
    0.45
    Activations Density 0.045%

    No Known Activations