© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14152
    Prev
    Next
    INDEX
    Explanations

    references to a specific company or organization involved in nuclear energy development

    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
    contentLoaded
    -0.88
    IntoConstraints
    -0.87
    NameInMap
    -0.82
    Personensuche
    -0.81
     dAtA
    -0.79
    isContained
    -0.74
     NSCoder
    -0.73
     our
    -0.72
     arşivlendi
    -0.70
    CppMethod
    -0.70
    POSITIVE LOGITS
    WE
    2.41
     WE
    2.27
     Wea
    0.91
    Wea
    0.90
    wea
    0.84
     wea
    0.80
    WEI
    0.68
     Weed
    0.57
    OWE
    0.57
     weights
    0.56
    Activations Density 0.002%

    No Known Activations