© 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. 7421
    Prev
    Next
    INDEX
    Explanations

    references to the suppression or exclusion of evidence or 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
    Not in Any Lists

    No Comments

    Negative Logits
    PositiveButton
    -0.65
    ngdoc
    -0.64
    lementary
    -0.61
    Ramb
    -0.60
    segno
    -0.59
     Duf
    -0.58
    NameInMap
    -0.57
    EndProject
    -0.57
    RegisterType
    -0.57
    AndEndTag
    -0.56
    POSITIVE LOGITS
     suppress
    2.83
     suppressed
    2.63
     suppression
    2.44
     suppressing
    2.36
     suppresses
    2.36
     Suppression
    2.31
    suppress
    2.06
     suppressor
    1.88
    Suppress
    1.84
     Supp
    1.14
    Activations Density 0.014%

    No Known Activations