© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12833
    Prev
    Next
    INDEX
    Explanations

    references to the NSA or similar government agencies, especially in contexts involving secrecy, cybersecurity, or covert activities

    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
    ":["
    -0.66
    })}\
    -0.56
     Gibson
    -0.54
     Vegas
    -0.53
    OnItem
    -0.52
     VEGAS
    -0.51
    combin
    -0.50
    перь
    -0.49
    yoto
    -0.48
    enton
    -0.48
    POSITIVE LOGITS
    uts
    1.58
    UTS
    1.15
     asymptotically
    0.91
     تضيفلها
    0.83
     NSA
    0.79
     beginnetje
    0.72
     propOrder
    0.68
     facto
    0.65
     autorytatywna
    0.64
    IBOutlet
    0.63
    Activations Density 0.003%

    No Known Activations