© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 77
    Prev
    Next
    INDEX
    Explanations

    text from physics papers related to quantum field theory, as it finds terms like Yang-Mills theory, fermions, actions, gauge symmetries, lorentz.

    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.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esgue
    -0.61
    SourceChecksum
    -0.60
    godic
    -0.58
     giacca
    -0.56
     defaultstate
    -0.55
     bocca
    -0.54
     Dwyer
    -0.54
    تقاوى
    -0.54
     miglia
    -0.52
    lceil
    -0.51
    POSITIVE LOGITS
     autorytatywna
    0.69
     tensor
    0.63
    Portail
    0.59
     Ons
    0.57
     OFDb
    0.56
     spin
    0.56
    Ons
    0.55
    Portale
    0.54
    Erstellt
    0.54
    apimachinery
    0.54
    Activations Density 6.248%

    No Known Activations