© 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. 17107
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to geometry and algebra

    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
     autorytatywna
    -0.68
    
    -0.64
    writeFieldEnd
    -0.63
    balleur
    -0.51
     الحره
    -0.50
    ✨:
    -0.50
    RegistryLite
    -0.50
     jspb
    -0.50
    WriteAttribute
    -0.50
    antaine
    -0.49
    POSITIVE LOGITS
    größern
    0.61
     incomplète
    0.60
     GenerationType
    0.60
     vocales
    0.60
     impea
    0.59
     مواليد
    0.57
     suivants
    0.57
    ataire
    0.56
     leão
    0.56
    cicle
    0.55
    Activations Density 0.081%

    No Known Activations