© 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. 18-RES-MATRYOSHKA-DC
    7. 493
    Prev
    Next
    INDEX
    Explanations

    uses of the verb "do" generally surrounding negatives, comparisons, or questions

    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/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.71
    RectangleBorder
    -0.69
     TextInputType
    -0.64
    Portale
    -0.62
     textStatus
    -0.59
     <<<<<<<<<<<<<<
    -0.57
    SuccessListener
    -0.57
    mientos
    -0.55
     betweenstory
    -0.54
    ựu
    -0.54
    POSITIVE LOGITS
     nothing
    0.75
     not
    0.70
     does
    0.69
     وتسجيلات
    0.68
     things
    0.66
     away
    0.63
     Does
    0.63
     indeed
    0.63
    omsday
    0.61
     well
    0.60
    Activations Density 1.141%

    No Known Activations