© 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. 97096
    Prev
    Next
    INDEX
    Explanations

    technical / code / scientific

    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
    webElement
    -0.71
    исленность
    -0.71
     تضيفلها
    -0.67
    WriteTagHelper
    -0.66
    awtextra
    -0.65
    ölkerung
    -0.65
    RetentionPolicy
    -0.63
    :✨
    -0.62
     متعلقه
    -0.62
    fromnode
    -0.61
    POSITIVE LOGITS
    ers
    0.53
    CDC
    0.49
     floor
    0.47
    Floor
    0.47
    putExtra
    0.45
    ooze
    0.45
     Decke
    0.45
    )?.
    0.45
     Floor
    0.43
     bedo
    0.42
    Activations Density 0.109%

    No Known Activations