© 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. 22791
    Prev
    Next
    INDEX
    Explanations

    conditional phrases relating to alternative scenarios or explanations

    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
     &___
    -0.66
    addComponent
    -0.55
     spéciaux
    -0.55
    原始内容存档于
    -0.54
     especiais
    -0.52
     intptr
    -0.51
    addGap
    -0.50
    filepath
    -0.50
    と言って
    -0.48
     CWE
    -0.48
    POSITIVE LOGITS
    CPtr
    0.77
    BeginInit
    0.60
    Begriffsklä
    0.57
    ThroughAttribute
    0.57
    ollectionView
    0.55
    dymyr
    0.54
    ytick
    0.54
    PreInfinity
    0.53
     Viter
    0.52
     Drapeau
    0.52
    Activations Density 0.178%

    No Known Activations