© 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. 9554
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical concepts and ghost variables in physical theories

    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
    )».
    -0.63
    以上就是
    -0.59
     doubtnut
    -0.58
    rrggbb
    -0.56
     Ambrose
    -0.56
     papaya
    -0.55
    ()][
    -0.55
     passada
    -0.55
    ására
    -0.54
     gynhyrchwyd
    -0.54
    POSITIVE LOGITS
     SEDS
    0.62
    dero
    0.46
     defaultstate
    0.46
     esterni
    0.45
     pié
    0.45
     cosa
    0.45
    BASELINE
    0.45
    FileDescriptor
    0.45
     оригіналу
    0.44
    RetentionPolicy
    0.43
    Activations Density 0.036%

    No Known Activations