© 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. 0-RES-MATRYOSHKA-DC
    7. 10739
    Prev
    Next
    INDEX
    Explanations

    references or mentions of supplementary information or supportive content

    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
     preceded
    -0.75
    AnchorTagHelper
    -0.69
     оригіналу
    -0.68
    Sucesor
    -0.65
     accompanied
    -0.64
    accompanied
    -0.64
    IsPostBack
    -0.62
     Normdatei
    -0.60
    ✭✭
    -0.58
    picasso
    -0.57
    POSITIVE LOGITS
     accompanying
    1.85
    companying
    0.88
    WebElementEntity
    0.74
     propOrder
    0.60
     mergeFrom
    0.59
    Portail
    0.56
    astify
    0.56
     blending
    0.55
     perdana
    0.55
    PerformLayout
    0.54
    Activations Density 0.001%

    No Known Activations