© 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. 0-CLT-HP
    7. 93835
    Prev
    Next
    INDEX
    Explanations

    played

    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
     played
    -1.09
     lived
    -1.05
     used
    -0.96
     worked
    -0.96
    used
    -0.95
    Used
    -0.82
     Used
    -0.81
     fought
    -0.79
     acted
    -0.79
     Played
    -0.78
    POSITIVE LOGITS
     initComponents
    0.61
    MessageTagHelper
    0.59
    AutoScale
    0.59
    MemoryWarning
    0.58
    InstanceState
    0.58
    setContentView
    0.57
    setVerticalGroup
    0.57
    AsUp
    0.57
     nakalista
    0.57
    راسیون
    0.56
    Activations Density 0.044%

    No Known Activations