© 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. 3391
    Prev
    Next
    INDEX
    Explanations

    annotations or placeholders in code snippets

    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
    TagMode
    -0.61
    Geplaatst
    -0.58
    aarrggbb
    -0.54
    localctx
    -0.52
     незавершена
    -0.52
    genheiten
    -0.51
     věci
    -0.51
     SUDOC
    -0.50
     perek
    -0.50
     SWIG
    -0.50
    POSITIVE LOGITS
    InvalidProtocol
    0.67
     fevere
    0.64
    IBOutlet
    0.63
    InjectAttribute
    0.62
     تضيفلها
    0.62
     Chrift
    0.61
     doInBackground
    0.60
    ChildScrollView
    0.59
     Chriftian
    0.59
    ftagPool
    0.59
    Activations Density 0.286%

    No Known Activations