© 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. 3-RES-MATRYOSHKA-DC
    7. 2837
    Prev
    Next
    INDEX
    Explanations

    the word "regardless"

    oai_token-act-pair · gemini-2.0-flash
    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
     Exacts
    -0.81
     Himo
    -0.81
    StructEnd
    -0.79
     Normdatei
    -0.75
    )];
    -0.75
    AccessorTable
    -0.74
    InjectAttribute
    -0.73
     kasarigan
    -0.72
    >(&
    -0.72
    TintMode
    -0.70
    POSITIVE LOGITS
     regardless
    2.59
    regardless
    2.42
     Regardless
    2.38
    Regardless
    2.31
     irrespective
    1.89
    ardless
    1.16
     uan
    1.14
     despite
    1.12
    dientemente
    1.10
    无论
    1.09
    Activations Density 0.003%

    No Known Activations