© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 11144
    Prev
    Next
    INDEX
    Explanations

    references to the concept of giving commands or issuing orders

    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
    PerformLayout
    -0.77
    ImageContext
    -0.69
     EconPapers
    -0.69
    aarrggbb
    -0.66
     @"/
    -0.65
    usermodel
    -0.63
    
    -0.60
    Personendaten
    -0.60
     Dictionary
    -0.59
    HtmlAttribute
    -0.59
    POSITIVE LOGITS
     dictate
    3.14
     dictates
    2.89
     dictated
    2.84
     dictation
    1.27
     dict
    0.81
     dikt
    0.78
     impone
    0.71
     stipul
    0.69
     dicta
    0.69
     prescribes
    0.63
    Activations Density 0.003%

    No Known Activations