© 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. 31872
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts in significance or quality

    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
     Majefty
    -0.97
    OGND
    -0.90
     Jefus
    -0.87
     ſta
    -0.87
     faſt
    -0.86
    存于互联网档案馆
    -0.85
     Shakspeare
    -0.81
     Anſ
    -0.81
     purpoſe
    -0.79
     quæ
    -0.77
    POSITIVE LOGITS
     nor
    0.53
     or
    0.52
     stra
    0.52
    gios
    0.49
    .
    0.47
    dir
    0.44
    Бли
    0.44
     in
    0.43
     sı
    0.42
    gione
    0.41
    Activations Density 0.012%

    No Known Activations