© 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. 570
    Prev
    Next
    INDEX
    Explanations

    the word "support" no matter the context

    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
     Fleming
    -0.70
    DeleteBehavior
    -0.63
    JDK
    -0.62
    HandlerContext
    -0.59
    printStackTrace
    -0.57
    jsonwebtoken
    -0.55
     Sơ
    -0.54
    ✨:
    -0.54
    ebles
    -0.54
    目を
    -0.54
    POSITIVE LOGITS
     support
    3.08
     Support
    2.89
    support
    2.88
    Support
    2.81
     SUPPORT
    2.67
     supports
    2.59
    SUPPORT
    2.52
     Supports
    2.52
     supporting
    2.44
    Supports
    2.38
    Activations Density 0.454%

    No Known Activations