© 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. 17070
    Prev
    Next
    INDEX
    Explanations

    specific numerical values in a scientific or technical context

    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
     Gerr
    -0.76
    sek
    -0.74
     Pell
    -0.72
    nextElement
    -0.67
     nuoc
    -0.67
    ••••
    -0.65
     royaume
    -0.65
     Becca
    -0.65
    Externí
    -0.65
     Gage
    -0.65
    POSITIVE LOGITS
    InputTagHelper
    0.81
    rawDesc
    0.69
    Архівовано
    0.67
    
    0.66
    مراجع
    0.66
    ·
    0.66
    DockStyle
    0.63
    idjan
    0.63
    __*/
    0.63
     PIB
    0.63
    Activations Density 0.002%

    No Known Activations