© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 574
    Prev
    Next
    INDEX
    Explanations

    the word "digit"

    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
    othelioma
    -0.66
     Völker
    -0.60
    getMock
    -0.60
     Winaray
    -0.59
    Soda
    -0.58
    Wiki
    -0.56
    awaiter
    -0.56
    Descripción
    -0.54
     Kins
    -0.54
    illotine
    -0.52
    POSITIVE LOGITS
     digit
    2.83
     digits
    2.55
    digit
    2.53
     Digit
    2.53
    Digit
    2.33
    digits
    2.23
     DIGIT
    2.08
     Dig
    2.00
    Digits
    1.99
    DIGIT
    1.92
    Activations Density 0.202%

    No Known Activations