© 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. 3-RES-MATRYOSHKA-DC
    7. 1713
    Prev
    Next
    INDEX
    Explanations

    the word "references"

    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
     propOrder
    -0.74
    SizeF
    -0.66
    WidgetItem
    -0.64
    CAPTION
    -0.62
    atelier
    -0.60
     ſche
    -0.58
     Olsson
    -0.57
     ―――――
    -0.57
    athion
    -0.57
    Upd
    -0.57
    POSITIVE LOGITS
     reference
    2.66
     references
    2.58
     refer
    2.47
     References
    2.33
     Reference
    2.31
     Refer
    2.30
    reference
    2.25
    refer
    2.20
     referencing
    2.19
    References
    2.17
    Activations Density 0.356%

    No Known Activations