© 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. 12-RES-MATRYOSHKA-DC
    7. 14306
    Prev
    Next
    INDEX
    Explanations

    references to international operations and networking within professional contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     nationally
    -0.47
     heng
    -0.42
    able
    -0.42
    ()]);
    -0.42
     Eastwood
    -0.41
     grail
    -0.40
     Series
    -0.40
     Bersama
    -0.40
     series
    -0.40
    Dispatcher
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    0.94
    MemoryWarning
    0.85
     estekak
    0.79
     ModelExpression
    0.69
    цездатний
    0.68
    новниш
    0.66
     GenerationType
    0.62
    ConstraintMaker
    0.62
    Clik
    0.60
     ويكيپيديا
    0.60
    Activations Density 0.031%

    No Known Activations