© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2930
    Prev
    Next
    INDEX
    Explanations

    specific HTML tags or markup-related tokens

    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
    AddTagHelper
    -0.96
    ReusableCell
    -0.75
    IntoConstraints
    -0.73
     uska
    -0.72
    ulemon
    -0.72
    apimachinery
    -0.71
    AndEndTag
    -0.69
     saites
    -0.66
    =|
    -0.65
    
    -0.65
    POSITIVE LOGITS
    >&
    1.16
    ">&
    1.03
    ;&
    0.74
     '&
    0.63
     chofe
    0.59
     "&
    0.59
    Насе
    0.58
     compétence
    0.57
    jár
    0.57
     cæ
    0.56
    Activations Density 0.024%

    No Known Activations