© 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. 388
    Prev
    Next
    INDEX
    Explanations

    the word "more", and also numbers, and words indicating a small amount

    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
     Efq
    -0.81
    principalColumn
    -0.80
     jScrollPane
    -0.79
    Према
    -0.79
     groote
    -0.78
     quæ
    -0.77
     ſmall
    -0.77
    /**
    -0.76
    GREAT
    -0.74
     pauvre
    -0.73
    POSITIVE LOGITS
     more
    2.78
    more
    2.45
    More
    2.42
     More
    2.39
     MORE
    2.38
    MORE
    2.02
     lebih
    1.79
     mehr
    1.65
     bardziej
    1.56
     więcej
    1.55
    Activations Density 1.307%

    No Known Activations