© 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. 14517
    Prev
    Next
    INDEX
    Explanations

    numerical values related to mathematical expressions or 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
    Fazit
    -0.77
     INTERESAR
    -0.69
    rzost
    -0.69
    Rhestr
    -0.68
    eavour
    -0.66
    voltaic
    -0.63
    cury
    -0.61
    Coucou
    -0.61
    لاعات
    -0.61
    ofern
    -0.60
    POSITIVE LOGITS
     CreateTagHelper
    0.60
    mang
    0.46
     AssemblyProduct
    0.44
     ModelExpression
    0.43
    WebElementEntity
    0.43
     surla
    0.43
     []:
    0.41
    LElement
    0.41
    StateList
    0.41
    __':
    0.41
    Activations Density 0.061%

    No Known Activations