© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1991
    Prev
    Next
    INDEX
    Explanations

    article excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     penn
    -0.51
    :
    -0.47
     setInterval
    -0.46
     runt
    -0.45
    RepeatedField
    -0.45
     fast
    -0.41
     ring
    -0.40
    ).
    -0.40
    :+
    -0.40
     onStart
    -0.40
    POSITIVE LOGITS
    AddTagHelper
    0.73
    GenerationType
    0.66
    MLLoader
    0.66
    onViewCreated
    0.65
    DebuggerNonUser
    0.64
     supérieurs
    0.62
    lorette
    0.61
     بيها
    0.60
    Referencies
    0.59
    BeginInit
    0.57
    Activations Density 0.003%

    No Known Activations