© 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. 6141
    Prev
    Next
    INDEX
    Explanations

    references to proofs and their structure in mathematical 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
     للاسماء
    -0.72
     disambiguazione
    -0.71
     nahilalakip
    -0.71
    Hozzáférés
    -0.71
     חיצוניים
    -0.70
    HasForeignKey
    -0.70
     insuffisamment
    -0.69
    OGND
    -0.69
    principalColumn
    -0.69
    Tembelea
    -0.69
    POSITIVE LOGITS
     proofs
    1.01
    Proof
    0.94
    proof
    0.90
     Proofs
    0.86
     Proof
    0.85
     PROOF
    0.83
    PROOF
    0.79
     proof
    0.77
    führt
    0.69
    proofing
    0.69
    Activations Density 0.039%

    No Known Activations