© 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. 5669
    Prev
    Next
    INDEX
    Explanations

    references to qualified immunity

    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
     ویکی‌پدی
    -0.66
     useDispatch
    -0.65
     déchir
    -0.63
     للاسماء
    -0.63
    PreExecute
    -0.60
    hadur
    -0.59
    ⓧ
    -0.59
    theless
    -0.59
     desesper
    -0.59
    ochlor
    -0.58
    POSITIVE LOGITS
     immunity
    2.89
     Immunity
    2.42
    immunity
    2.02
    munity
    1.15
     immune
    0.77
     impunity
    0.72
    immune
    0.70
     inmun
    0.70
     Immune
    0.66
     indem
    0.65
    Activations Density 0.006%

    No Known Activations