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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15579
    Prev
    Next
    INDEX
    Explanations

    cases of indistinguishability or similarity in textual or legal contexts

    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
    PerformLayout
    -0.80
     Roskov
    -0.75
     <>",
    -0.74
     BorderRadius
    -0.62
    حياتها
    -0.61
     FetchType
    -0.57
    AsUp
    -0.56
    nextProps
    -0.56
     Holman
    -0.56
    Données
    -0.55
    POSITIVE LOGITS
     indistingu
    3.39
     distinguishable
    1.43
    distingu
    1.02
     unrecogn
    0.88
     undist
    0.79
     inseparable
    0.79
     indistinct
    0.66
     interchangeable
    0.65
    matchCondition
    0.63
    migrationBuilder
    0.61
    Activations Density 0.001%

    No Known Activations