© 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. 17223
    Prev
    Next
    INDEX
    Explanations

    references to specific cases or instances in legal discussions

    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
    Negative Logits
    ContentAsync
    -1.09
    setVerticalGroup
    -1.09
    ValueStyle
    -0.95
     JpaRepository
    -0.84
     CreateTagHelper
    -0.84
    WebServlet
    -0.82
    principalTable
    -0.79
    MessageOf
    -0.79
    AddTagHelper
    -0.77
     désolés
    -0.77
    POSITIVE LOGITS
    .
    0.55
     A
    0.46
     We
    0.45
    éről
    0.44
    üyada
    0.43
     Someone
    0.42
     runner
    0.42
     episódios
    0.42
    áról
    0.41
     defraud
    0.41
    Activations Density 0.015%

    No Known Activations