© 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. 4-CLT-HP
    4. 2360
    Prev
    Next
    INDEX
    Explanations

    referring to something

    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
     these
    -0.79
     those
    -0.68
     ones
    -0.63
    these
    -0.60
    These
    -0.60
     These
    -0.60
     them
    -0.54
     ComVisible
    -0.53
    مصادر
    -0.52
     estos
    -0.50
    POSITIVE LOGITS
     فريبيس
    0.79
    principalColumn
    0.69
     Beaches
    0.67
    WebElementEntity
    0.64
    StoryboardSegue
    0.62
     Minerals
    0.60
    IBOutlet
    0.60
     Gases
    0.60
     daarbij
    0.60
    UnsafeEnabled
    0.59
    Activations Density 0.018%

    No Known Activations