© 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. 17620
    Prev
    Next
    INDEX
    Explanations

    references to justifications or reasons in a legal context

    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
     whole
    -0.63
    erweise
    -0.56
    طيع
    -0.55
     predictable
    -0.53
    ÉL
    -0.52
    zeile
    -0.52
    ingly
    -0.52
    mated
    -0.52
    inor
    -0.52
    식
    -0.52
    POSITIVE LOGITS
     متعلقه
    0.90
    styleType
    0.70
    elemField
    0.69
    ItemBackground
    0.66
    InSection
    0.63
    SharedDtor
    0.63
    +#+#
    0.59
    jalá
    0.59
     }{@
    0.56
     nakalista
    0.56
    Activations Density 0.025%

    No Known Activations