© 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. 0-RES-MATRYOSHKA-DC
    7. 11291
    Prev
    Next
    INDEX
    Explanations

    references to legal or judicial concepts and citations

    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
    UserScript
    -0.63
    zzleHttp
    -0.62
    存于互联网档案馆
    -0.61
     تضيفلها
    -0.60
    WireFormat
    -0.59
    Portail
    -0.57
    XmlAccessorType
    -0.57
    WebServlet
    -0.55
    NameInMap
    -0.55
    antry
    -0.54
    POSITIVE LOGITS
    cion
    3.92
    acion
    1.75
    ciona
    1.48
    ACION
    1.47
    CION
    1.30
    cions
    1.21
    cionar
    1.17
    cione
    1.13
    cionado
    1.10
    cionada
    1.09
    Activations Density 0.001%

    No Known Activations