© 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. 30491
    Prev
    Next
    INDEX
    Explanations

    mathematical notation involving underlined variables and their properties

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.89
     Braw
    -0.84
    httphttps
    -0.80
     AppBundle
    -0.77
    GenerationType
    -0.76
    Rujuakan
    -0.72
    WriteBarrier
    -0.72
    galo
    -0.69
    ModelBuilder
    -0.69
     mergeFrom
    -0.68
    POSITIVE LOGITS
    underline
    1.72
    Underline
    1.07
     underline
    0.85
     Lindsey
    0.69
    Lindsey
    0.67
     Jacinto
    0.67
     Linder
    0.65
    Моло
    0.65
    huriyet
    0.64
     NSC
    0.63
    Activations Density 0.033%

    No Known Activations