© 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. 13484
    Prev
    Next
    INDEX
    Explanations

    references to boxed or packaged collections of media content

    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
     Efq
    -0.76
     ErrIntOverflow
    -0.75
    NameInMap
    -0.74
    inaison
    -0.71
     Jefus
    -0.64
     whoſe
    -0.63
    ]--;
    -0.62
    Portail
    -0.61
     <=",
    -0.60
     Monfieur
    -0.60
    POSITIVE LOGITS
     boxing
    2.92
    boxing
    2.81
    Boxing
    2.52
     Boxing
    2.48
     boxer
    2.05
     boxers
    1.91
    boxer
    1.57
     boxeo
    1.54
     Boxer
    1.19
    🥊
    1.03
    Activations Density 0.000%

    No Known Activations