© 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. 20670
    Prev
    Next
    INDEX
    Explanations

    HTML table elements and attributes

    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
    ⓧ
    -0.71
    ScopeManager
    -0.68
     FetchType
    -0.59
    BeginContext
    -0.56
     références
    -0.54
    脚注の使い方
    -0.54
    DoubleQuotes
    -0.54
    Facades
    -0.53
     HasFactory
    -0.52
     cse
    -0.51
    POSITIVE LOGITS
    TableHead
    1.01
    <thead>
    0.98
    thead
    0.62
    </thead>
    0.59
     Theodo
    0.55
    </caption>
    0.52
    Попис
    0.52
     autorité
    0.52
     ✭✭
    0.50
    zaamheid
    0.48
    Activations Density 0.010%

    No Known Activations