Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14269
    Prev
    Next
    INDEX
    Explanations

    the word "gate" in a discussion of transistors

    oai_token-act-pair · gemini-2.0-flash

    The neuron detects the word "gate" in electronic and computing contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @eugene
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/width_16k
    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
     gate
    -2.88
     Gate
    -2.67
    Gate
    -2.53
    gate
    -2.53
     gates
    -2.19
    GATE
    -2.05
    gates
    -1.94
     GATE
    -1.93
     Gates
    -1.61
    Gates
    -1.55
    POSITIVE LOGITS
     виправивши
    0.81
     AssemblyVersion
    0.80
    MigrationBuilder
    0.77
    bootstrapcdn
    0.72
    ViewFeatures
    0.69
    numerusform
    0.69
     CreateTagHelper
    0.68
     autorytatywna
    0.68
    UnsafeEnabled
    0.68
     pleaſure
    0.66
    Activations Density 0.662%

    No Known Activations