© 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. 0-CLT-HP
    4. 38353
    Prev
    Next
    INDEX
    Explanations

    sports

    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
     cool
    -0.66
     rueda
    -0.53
    ER
    -0.47
     dies
    -0.46
    COOL
    -0.46
    cool
    -0.45
     coolest
    -0.45
     depends
    -0.44
     COOL
    -0.44
    er
    -0.43
    POSITIVE LOGITS
     typelib
    1.02
     initComponents
    0.91
    Diweddarwch
    0.84
    ChildScrollView
    0.83
     GenerationType
    0.79
    Autoritní
    0.79
    Personendaten
    0.79
    ]")]
    0.78
    RegressionTest
    0.78
    ])):
    0.77
    Activations Density 1.231%

    No Known Activations