© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4518
    Prev
    Next
    INDEX
    Explanations

    references to terrorism and related threats

    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
    PropertyChanging
    -0.55
    ipro
    -0.51
    RegressionTest
    -0.48
    providedIn
    -0.48
     obro
    -0.47
    HasBeenSet
    -0.47
    much
    -0.46
    =’
    -0.46
    bihan
    -0.46
     Douglas
    -0.45
    POSITIVE LOGITS
    terror
    3.22
    Terror
    2.98
     Terror
    2.97
     terrorism
    2.88
     terror
    2.80
     terrorist
    2.73
     terrorists
    2.63
     Terrorism
    2.63
    terrorism
    2.47
     terrorismo
    2.11
    Activations Density 0.011%

    No Known Activations