© 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. 24-RES-MATRYOSHKA-DC
    7. 1589
    Prev
    Next
    INDEX
    Explanations

    terms and phrases used in theoretical physics papers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    Попис
    -0.55
    parsedMessage
    -0.55
     démon
    -0.53
     isInitialized
    -0.52
     proof
    -0.51
    libft
    -0.51
     Proof
    -0.51
    LookAnd
    -0.50
     <=",
    -0.50
    anii
    -0.48
    POSITIVE LOGITS
    脚注の使い方
    0.60
     AttributeSet
    0.57
     cleanest
    0.56
     defaultstate
    0.56
    ensus
    0.56
     חיצוניים
    0.56
    =$?
    0.56
    UrlResolution
    0.56
     Needless
    0.54
    lingua
    0.54
    Activations Density 1.705%

    No Known Activations