© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5009
    Prev
    Next
    INDEX
    Explanations

    references to specific numbered items or entities

    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
     đ
    -0.63
    broek
    -0.55
     ma
    -0.53
     us
    -0.52
    simo
    -0.51
     one
    -0.51
     RE
    -0.50
     fellow
    -0.50
     st
    -0.49
    WebElementEntity
    -0.49
    POSITIVE LOGITS
    AddTagHelper
    0.86
     ་་
    0.86
     Efq
    0.85
     XNUMX
    0.82
     itſelf
    0.79
     Theſe
    0.76
    цездатний
    0.74
     blest
    0.69
     Samaria
    0.69
    ^(@)
    0.68
    Activations Density 0.316%

    No Known Activations