© 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. 1-CLT-HP
    7. 9331
    Prev
    Next
    INDEX
    Explanations

    to

    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
     فريبيس
    -0.87
    rungsseite
    -0.78
    pexpr
    -0.65
    RefNanny
    -0.64
    脚注の使い方
    -0.63
     propOrder
    -0.60
    WebVitals
    -0.60
     hinaus
    -0.57
    jalá
    -0.56
     putea
    -0.56
    POSITIVE LOGITS
     recognising
    0.93
     releasing
    0.88
     producing
    0.88
     integrating
    0.86
     treating
    0.86
     examining
    0.83
     detecting
    0.82
     injecting
    0.82
     predicting
    0.81
     rejecting
    0.81
    Activations Density 0.016%

    No Known Activations