© 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. 42264
    Prev
    Next
    INDEX
    Explanations

    tuned/remotely

    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
     tune
    -0.90
    tune
    -0.79
    tun
    -0.78
     tuned
    -0.76
     tuning
    -0.76
     Tune
    -0.72
    WebVitals
    -0.71
    PerformLayout
    -0.71
    jgl
    -0.69
     ujednoznacz
    -0.69
    POSITIVE LOGITS
     استنادى
    0.57
     papyrus
    0.50
     chilena
    0.47
     EconPapers
    0.45
    Perú
    0.45
     mexicana
    0.44
    astéro
    0.44
     Aeropuerto
    0.44
     garda
    0.44
    friend
    0.44
    Activations Density 0.041%

    No Known Activations