© 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. 6-RES-MATRYOSHKA-DC
    4. 900
    Prev
    Next
    INDEX
    Explanations

    the word "sub" in various contexts (HTML, biology, programming)

    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
     }}"></
    -1.04
     Floren
    -0.94
     ?>">
    -0.89
     kaynağından
    -0.89
     defaultstate
    -0.84
    PageFactory
    -0.84
    parseColor
    -0.83
     BorderRadius
    -0.83
    Portail
    -0.80
     Meksiku
    -0.79
    POSITIVE LOGITS
     sub
    2.02
     Sub
    1.88
    SUB
    1.84
     SUB
    1.82
    sub
    1.77
    Sub
    1.71
     subs
    1.62
     getSub
    1.41
    getSub
    1.34
    サブ
    1.33
    Activations Density 0.463%

    No Known Activations