© 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. 23403
    Prev
    Next
    INDEX
    Explanations

    patterns of approval and rejection, particularly in contexts involving lists or tables

    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
     Monfieur
    -0.87
    Personensuche
    -0.75
    ArgsConstructor
    -0.75
     myſelf
    -0.70
     Cæsar
    -0.68
    awtextra
    -0.68
     becauſe
    -0.67
     themſelves
    -0.67
     ainfi
    -0.65
     Majefty
    -0.64
    POSITIVE LOGITS
    úrese
    0.53
    PerformLayout
    0.49
    initro
    0.49
    참고
    0.48
    ыгана
    0.47
     дописавши
    0.46
    pyx
    0.46
    runge
    0.46
     sc
    0.44
    Rational
    0.44
    Activations Density 0.023%

    No Known Activations