© 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. 14961
    Prev
    Next
    INDEX
    Explanations

    labels and mathematical notation

    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
    twimg
    -0.91
     propOrder
    -0.89
    migrationBuilder
    -0.82
    Autoritní
    -0.81
    SharedCtor
    -0.80
    曖昧さ回避
    -0.75
     externi
    -0.74
     CreateTagHelper
    -0.73
    évaluateur
    -0.73
    addCriterion
    -0.71
    POSITIVE LOGITS
     sejauh
    0.52
     کاش
    0.50
     precedenti
    0.47
    patent
    0.46
     hvorfor
    0.45
    AssignableFrom
    0.45
    Bonjour
    0.45
    StringCopy
    0.44
     menunggu
    0.44
    DataURL
    0.44
    Activations Density 0.001%

    No Known Activations