© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1686
    Prev
    Next
    INDEX
    Explanations

    legitimacy and origins

    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
     Theſe
    -1.04
     Shakspeare
    -0.92
    ORIGIN
    -0.88
    origin
    -0.84
     Efq
    -0.83
     purpoſe
    -0.81
     reaſon
    -0.81
     Houſe
    -0.80
     Origin
    -0.80
     pleaſure
    -0.80
    POSITIVE LOGITS
    AsUp
    0.68
    Ecotoxicity
    0.56
     La
    0.53
    Показать
    0.52
    atorship
    0.52
    LabelTagHelper
    0.50
     can
    0.49
     il
    0.48
    ality
    0.47
    ally
    0.47
    Activations Density 0.100%

    No Known Activations