© 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. 3695
    Prev
    Next
    INDEX
    Explanations

    references to specific technical standards, particularized instances, or detailed definitions

    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
     hashCode
    -0.50
     držav
    -0.48
    ServiceImpl
    -0.46
    дцать
    -0.44
    throm
    -0.43
    ו
    -0.43
    字
    -0.42
     økonom
    -0.42
     stø
    -0.42
     (
    -0.41
    POSITIVE LOGITS
    expandindo
    1.29
    Portale
    1.00
     CURIAM
    0.98
    Datuak
    0.90
    parsedMessage
    0.89
    webElementXpaths
    0.88
     noDo
    0.87
    دانشنامهٔ
    0.85
     kasarigan
    0.81
    RegistryLite
    0.81
    Activations Density 0.777%

    No Known Activations