© 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. 0-CLT-HP
    4. 1741
    Prev
    Next
    INDEX
    Explanations

    standards/licenses

    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
    <bos>
    -0.61
    เยอะ
    -0.52
     clearfix
    -0.51
     médaille
    -0.50
     denoted
    -0.48
     aquilo
    -0.45
     sounded
    -0.44
    typeparam
    -0.44
     maggiori
    -0.44
     floated
    -0.44
    POSITIVE LOGITS
     تضيفلها
    0.77
     propOrder
    0.71
     gynhyrchwyd
    0.69
    Personensuche
    0.69
    XmlAccessType
    0.66
    richTextPanel
    0.65
    AnchorStyles
    0.63
    webElement
    0.62
    ANTY
    0.60
    InputBorder
    0.60
    Activations Density 0.060%

    No Known Activations