© 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. 22-RES-MATRYOSHKA-DC
    7. 1907
    Prev
    Next
    INDEX
    Explanations

    the word "due"

    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.22.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.22.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
    SourceChecksum
    -0.77
    ValueStyle
    -0.77
    contentLoaded
    -0.75
     betweenstory
    -0.75
     NSCoder
    -0.74
    IUrlHelper
    -0.73
     ProtoMessage
    -0.66
    parsedMessage
    -0.66
    oa̍t
    -0.66
     CreateTagHelper
    -0.66
    POSITIVE LOGITS
     diligence
    0.87
     due
    0.74
     date
    0.67
     lack
    0.66
     Due
    0.61
     Dili
    0.61
     partly
    0.60
    Debido
    0.57
     mainly
    0.57
    Due
    0.56
    Activations Density 0.083%

    No Known Activations