© 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. 4197
    Prev
    Next
    INDEX
    Explanations

    patterns corresponding to specific coded sequences or formatted strings

    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
    ookie
    -0.48
     aceptas
    -0.47
    Mascul
    -0.45
    нрави
    -0.45
    م
    -0.44
    έρ
    -0.43
    Uninitialized
    -0.43
    лец
    -0.42
    FE
    -0.40
    SetFont
    -0.40
    POSITIVE LOGITS
    __':
    1.01
    __":
    0.85
    PerformLayout
    0.80
    __':
    0.77
     متعلقه
    0.71
    RegistryLite
    0.71
     numberWith
    0.71
     виправивши
    0.70
     насељу
    0.70
    جغرافيا
    0.68
    Activations Density 0.022%

    No Known Activations