© 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. 1393
    Prev
    Next
    INDEX
    Explanations

    the word "action" and related programming actions

    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
    клопе
    -0.91
     فريبيس
    -0.90
     Púb
    -0.89
     Majefty
    -0.83
    InjectAttribute
    -0.82
    WebVitals
    -0.81
     للاسماء
    -0.81
    BagLayout
    -0.80
    SequentialGroup
    -0.79
    UrlResolution
    -0.78
    POSITIVE LOGITS
     action
    3.39
     Action
    3.19
     ACTION
    3.02
    action
    2.98
    Action
    2.98
     actions
    2.72
     Actions
    2.67
    ACTION
    2.64
    Actions
    2.53
    actions
    2.48
    Activations Density 0.167%

    No Known Activations