© 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. 15645
    Prev
    Next
    INDEX
    Explanations

    legal and financial terminology related to debt cancellation and exclusions applicable to taxable income

    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
    mlı
    -0.57
     valable
    -0.53
    λέ
    -0.50
    irus
    -0.50
     laminated
    -0.48
     visuel
    -0.48
     récol
    -0.47
    culi
    -0.47
    ้ว
    -0.47
    perma
    -0.46
    POSITIVE LOGITS
     propOrder
    0.62
    principalTable
    0.56
     muualla
    0.52
     fieldNum
    0.50
    addPreferredGap
    0.50
    Activities
    0.50
    GOTREF
    0.49
    кобрита
    0.49
     onData
    0.49
     '/',
    0.48
    Activations Density 0.078%

    No Known Activations