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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15932
    Prev
    Next
    INDEX
    Explanations

    the presence of employment-related words, specifically the verb "employ" in various contexts

    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
     صوتيه
    -0.76
    ValueStyle
    -0.75
    ьаж
    -0.74
    contentLoaded
    -0.74
     ModelExpression
    -0.73
    Życiorys
    -0.70
     betweenstory
    -0.70
    ViewImports
    -0.69
    StandardCharsets
    -0.69
     ReactDOM
    -0.68
    POSITIVE LOGITS
     employ
    2.39
     Employ
    1.55
    employ
    1.24
    Employ
    1.17
     employs
    1.05
     employing
    0.76
     emple
    0.65
    hella
    0.59
    emplo
    0.55
     emplo
    0.54
    Activations Density 0.004%

    No Known Activations