© 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. 6732
    Prev
    Next
    INDEX
    Explanations

    specific symbols or terms associated with mathematical constants and variables

    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
     getItemCount
    -0.88
     Marien
    -0.82
     feroit
    -0.82
     étoit
    -0.81
     auroit
    -0.81
    ⓘ
    -0.81
     giebt
    -0.81
    EReference
    -0.74
     jopa
    -0.73
     réfrig
    -0.73
    POSITIVE LOGITS
    lambda
    1.60
     λ
    1.51
     lambda
    1.28
    λ
    1.21
     Lamb
    0.97
     lamb
    0.91
     Lam
    0.90
    Lamb
    0.89
     Lambda
    0.88
    Wavelength
    0.86
    Activations Density 0.065%

    No Known Activations