© 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. 6-RES-MATRYOSHKA-DC
    7. 950
    Prev
    Next
    INDEX
    Explanations

    the word "just" followed by an action verb or qualifier

    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
    endregion
    -0.84
    findpost
    -0.81
    enderror
    -0.77
    
    -0.77
    Autoritní
    -0.76
     Mushrooms
    -0.74
    LabelTagHelper
    -0.73
    Eileen
    -0.73
    ंदीखरीदारी
    -0.73
    styleUrls
    -0.71
    POSITIVE LOGITS
    just
    1.31
    Just
    1.31
     Just
    1.29
    JUST
    1.24
     JUST
    1.23
     just
    1.22
     Simplemente
    1.04
     Justine
    1.01
     simply
    0.95
    simply
    0.95
    Activations Density 0.349%

    No Known Activations