© 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. 23577
    Prev
    Next
    INDEX
    Explanations

    numerical representations and scientific measurements in texts

    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
    WireFormatLite
    -0.52
     Forsyth
    -0.46
     considerato
    -0.45
     tombe
    -0.45
    能源
    -0.43
     musicale
    -0.43
     görünü
    -0.42
     SFP
    -0.42
    Dona
    -0.42
     Lino
    -0.42
    POSITIVE LOGITS
    TagMode
    0.80
    IsContent
    0.74
    ItemBackground
    0.70
    __':
    0.66
    dafx
    0.62
    StructEnd
    0.62
     protoimpl
    0.60
    UnsafeEnabled
    0.60
     @"/
    0.59
    PerformLayout
    0.57
    Activations Density 0.045%

    No Known Activations