© 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. 0-RES-MATRYOSHKA-DC
    7. 12385
    Prev
    Next
    INDEX
    Explanations

    instances of commanding or command-related language

    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
     صوتيه
    -0.52
    oredCriteria
    -0.49
    scrollLeft
    -0.48
    lainen
    -0.46
    ież
    -0.45
     Songtext
    -0.44
    ρια
    -0.44
     Princip
    -0.43
    Sew
    -0.42
    ienta
    -0.42
    POSITIVE LOGITS
     commanded
    2.11
     commanding
    1.52
     Commanding
    1.29
    脚注の使い方
    0.82
     يتيمه
    0.81
    kloped
    0.75
     CreateTagHelper
    0.74
    Autoritní
    0.73
    AccessorTable
    0.71
     مُعرِّف
    0.70
    Activations Density 0.005%

    No Known Activations