© 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. 15616
    Prev
    Next
    INDEX
    Explanations

    mentions of arrests or being arrested

    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
    ंदीखरीदारी
    -0.63
     downstream
    -0.60
    genossen
    -0.60
    cipation
    -0.59
     Dijk
    -0.59
    interopRequire
    -0.58
    Upstream
    -0.58
     Upstream
    -0.57
     arrest
    -0.57
    chê
    -0.56
    POSITIVE LOGITS
     arrested
    2.09
     Arrested
    1.32
     detenido
    0.71
     detenidos
    0.66
    DebuggerNonUser
    0.61
    BeforeClass
    0.59
    TestingModule
    0.57
     newArray
    0.52
    بوابة
    0.50
    versible
    0.50
    Activations Density 0.003%

    No Known Activations