© 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. 5-CLT-HP
    4. 240
    Prev
    Next
    INDEX
    Explanations

    always

    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
    ⓒ
    -0.54
     unaware
    -0.53
     considered
    -0.52
     anonymity
    -0.50
    Württemberg
    -0.50
    bcryptjs
    -0.50
     adequate
    -0.50
     unsure
    -0.50
     مرئيه
    -0.50
    еремо
    -0.49
    POSITIVE LOGITS
     propOrder
    0.64
    IBOutlet
    0.60
     للاسماء
    0.55
     تضيفلها
    0.54
    érable
    0.54
    érables
    0.54
     utafiti
    0.52
     estekak
    0.52
    ginfo
    0.51
    ArgsConstructor
    0.51
    Activations Density 0.021%

    No Known Activations