© 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. 2-RES-MATRYOSHKA-DC
    7. 6197
    Prev
    Next
    INDEX
    Explanations

    references to situations involving imminent physical harm or risk of injury

    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
     AssemblyTitle
    -0.61
    oriasis
    -0.59
     precipitates
    -0.59
    mappedBy
    -0.58
     Opt
    -0.58
     choix
    -0.57
    Captor
    -0.57
     sahiptir
    -0.56
    riwal
    -0.56
    SpringRunner
    -0.56
    POSITIVE LOGITS
     danger
    2.81
     Danger
    2.59
     dangerous
    2.48
     dangers
    2.47
    Danger
    2.38
    danger
    2.36
    dangerous
    2.30
     Dangerous
    2.14
     Dangers
    2.09
    Dangerous
    2.05
    Activations Density 0.026%

    No Known Activations