© 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. 18-RES-MATRYOSHKA-DC
    7. 116
    Prev
    Next
    INDEX
    Explanations

    words related to international treaties and conflicts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Additionally
    -0.88
     incentiv
    -0.86
     meaningfully
    -0.85
     prioritize
    -0.84
     minimally
    -0.84
    Additionally
    -0.81
     proactively
    -0.80
     sourced
    -0.80
     toolkit
    -0.79
     estatus
    -0.78
    POSITIVE LOGITS
    ,—
    0.61
     muß
    0.59
     skall
    0.58
     pesce
    0.58
     réunions
    0.58
     habitudes
    0.57
     potuto
    0.57
     diatur
    0.57
     placés
    0.57
    faßt
    0.55
    Activations Density 6.102%

    No Known Activations