© 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. 4-CLT-HP
    7. 4936
    Prev
    Next
    INDEX
    Explanations

    follow

    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
     the
    -0.75
     various
    -0.65
    bukkit
    -0.64
    DrawerToggle
    -0.63
    ValueStyle
    -0.58
    外部連結
    -0.58
    uerre
    -0.57
    various
    -0.57
     a
    -0.56
     this
    -0.55
    POSITIVE LOGITS
    expandindo
    0.64
     يتيمه
    0.59
    cerol
    0.56
    rungsseite
    0.55
     principals
    0.47
    %:
    0.47
     geslacht
    0.47
    Revenir
    0.46
    esthetics
    0.46
     mxArray
    0.46
    Activations Density 0.004%

    No Known Activations