© 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. 2-RES-MATRYOSHKA-DC
    7. 2518
    Prev
    Next
    INDEX
    Explanations

    references to supplementary material or additional information

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     none
    -0.90
    none
    -0.88
     None
    -0.86
    None
    -0.85
     viewDidLoad
    -0.75
     empty
    -0.66
    Nil
    -0.66
     Nil
    -0.65
     nil
    -0.65
     ninguno
    -0.63
    POSITIVE LOGITS
     null
    2.19
    null
    1.98
     Null
    1.33
    Null
    1.23
    principalTable
    0.71
     оригіналу
    0.68
     subsoil
    0.65
     Meksiku
    0.64
    styleable
    0.63
     Rossa
    0.59
    Activations Density 0.011%

    No Known Activations