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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 75168
    Prev
    Next
    INDEX
    Explanations

    Technical or instructional texts

    np_max-act-logits · 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
    HandlerContext
    -0.58
    edb
    -0.50
    RenderAtEndOf
    -0.49
    vää
    -0.48
    ódó
    -0.48
    complexContent
    -0.47
     MyApp
    -0.47
    पया
    -0.46
     Numerade
    -0.45
    rolid
    -0.45
    POSITIVE LOGITS
    Step
    0.59
     Pot
    0.58
     pot
    0.57
     Step
    0.57
     com
    0.54
     Wagon
    0.53
    psack
    0.53
     Cooker
    0.53
     tables
    0.53
     Sink
    0.53
    Activations Density 0.000%

    No Known Activations