© 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. 0-RES-MATRYOSHKA-DC
    7. 11173
    Prev
    Next
    INDEX
    Explanations

    references to insiders or internal sources

    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
    RegistryLite
    -0.70
     Pfar
    -0.63
     pinulongan
    -0.59
    chymal
    -0.57
    UrlResolution
    -0.57
     EconPapers
    -0.56
    providedIn
    -0.55
    ยว
    -0.54
    atterson
    -0.54
     surla
    -0.54
    POSITIVE LOGITS
     Insider
    3.55
    Insider
    3.53
     insider
    3.38
    insider
    3.28
     insiders
    2.41
     outsider
    1.52
     Outsider
    1.25
     outsiders
    1.20
    setVerticalGroup
    0.76
    Outs
    0.76
    Activations Density 0.001%

    No Known Activations