© 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. 13639
    Prev
    Next
    INDEX
    Explanations

    the concept of representing or representation

    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
    DockStyle
    -0.62
    GraphicsUnit
    -0.56
    ãng
    -0.53
    Citiți
    -0.52
    __(/*!
    -0.50
    JAXB
    -0.50
     thang
    -0.49
    jfree
    -0.48
    wpi
    -0.47
     inflater
    -0.47
    POSITIVE LOGITS
    ReferenceEquals
    0.67
     represent
    0.64
    OGND
    0.60
    ulipas
    0.60
    Viited
    0.60
    OLVE
    0.60
     RuntimeError
    0.59
     représenter
    0.59
     purpoſe
    0.59
    resented
    0.57
    Activations Density 0.026%

    No Known Activations