© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91453
    Prev
    Next
    INDEX
    Explanations

    in

    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
     ComVisible
    -1.16
     EconPapers
    -1.13
     Normdatei
    -1.00
     تضيفلها
    -0.98
    DockStyle
    -0.96
     propOrder
    -0.96
    tvguidetime
    -0.94
    AutoScaleMode
    -0.94
     '\\;'
    -0.92
    InitVars
    -0.89
    POSITIVE LOGITS
     air
    0.44
    â
    0.44
    Ã
    0.40
     (
    0.40
     пер
    0.39
    fis
    0.39
     caught
    0.38
     ata
    0.38
    `
    0.38
     -
    0.37
    Activations Density 0.009%

    No Known Activations