© 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. 1-RES-MATRYOSHKA-DC
    7. 559
    Prev
    Next
    INDEX
    Explanations

    references to political violence, instability, or related conflicts

    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
     pinulongan
    -0.98
     betweenstory
    -0.81
     esternos
    -0.80
     surla
    -0.79
    ModelAdmin
    -0.79
     GenerationType
    -0.78
    InstrumentedTest
    -0.77
    cyklopedia
    -0.75
     BrowserModule
    -0.73
    WithIOException
    -0.73
    POSITIVE LOGITS
    ↵
    0.59
    <eos>
    0.46
     
    0.45
    excellents
    0.40
    名
    0.38
    ろ
    0.36
    ulously
    0.36
     tooth
    0.35
    動
    0.34
    i
    0.34
    Activations Density 11.485%

    No Known Activations