© 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. 24880
    Prev
    Next
    INDEX
    Explanations

    the term "chiral" in the context of theoretical physics

    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
     propOrder
    -0.91
    "}")
    -0.74
    mybatisplus
    -0.69
    __':
    -0.67
     peines
    -0.66
    __":
    -0.65
    Igles
    -0.64
    SceneManagement
    -0.63
     mahdol
    -0.63
    dcc
    -0.60
    POSITIVE LOGITS
     chiral
    1.40
    脚注の使い方
    0.69
    Chir
    0.68
     Soprano
    0.68
     PAP
    0.66
     Symmetry
    0.65
    JspWriter
    0.65
    ValueStyle
    0.63
    iral
    0.63
    inflater
    0.61
    Activations Density 0.000%

    No Known Activations