© 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. 15758
    Prev
    Next
    INDEX
    Explanations

    mentions of invasive or intrusive phenomena, particularly related to invasion or invasion-like processes

    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
    Personendaten
    -0.82
     Comprehensive
    -0.62
    Comprehensive
    -0.60
    UnifiedTopology
    -0.54
    EndGlobalSection
    -0.54
     comprehensive
    -0.54
    خابات
    -0.54
    ChildIndex
    -0.50
    braio
    -0.48
     comprehensively
    -0.48
    POSITIVE LOGITS
     invasive
    2.36
     Invasive
    2.16
    vasive
    1.30
    invasive
    0.95
     intrusive
    0.86
     invas
    0.75
    empêcher
    0.68
    __':
    0.63
    eway
    0.61
    ########.
    0.60
    Activations Density 0.000%

    No Known Activations