© 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. 10452
    Prev
    Next
    INDEX
    Explanations

    references to the term "Schne" and its variations, which may be related to specific theories or concepts in mathematics or physics, especially concerning "Schne" as part of broader scientific 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
    EDEFAULT
    -1.02
    Архівовано
    -1.01
    ViewFeatures
    -1.01
     ویکی‌پدیای
    -0.91
    TabStop
    -0.81
    存于互联网档案馆
    -0.81
     poffe
    -0.80
     tabPage
    -0.80
    djangoproject
    -0.79
     nahilalakip
    -0.79
    POSITIVE LOGITS
    Sch
    1.45
     Sch
    1.27
    sch
    1.27
     sch
    1.26
     SCH
    1.26
    SCH
    1.05
     Scho
    1.01
    scho
    0.98
     Schro
    0.93
     Schumacher
    0.93
    Activations Density 0.043%

    No Known Activations