© 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. 5-CLT-HP
    7. 96663
    Prev
    Next
    INDEX
    Explanations

    formatting characters/dividers

    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
     Normdatei
    -0.47
     filaments
    -0.40
     LCCN
    -0.38
     RDP
    -0.38
     covenants
    -0.37
     Leinster
    -0.36
     emperors
    -0.36
     giddy
    -0.36
    eará
    -0.36
     umbi
    -0.36
    POSITIVE LOGITS
     Мексичка
    0.90
    findpost
    0.75
    EDEFAULT
    0.75
    VersionUID
    0.73
    TagMode
    0.69
    resizingMask
    0.68
    tagHelperRunner
    0.68
     تضيفلها
    0.67
     ModelExpression
    0.66
    AddHtmlAttribute
    0.62
    Activations Density 0.005%

    No Known Activations