© 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. 10182
    Prev
    Next
    INDEX
    Explanations

    around

    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
     ddelweddau
    -0.71
     الدولى
    -0.66
    Around
    -0.65
    CloseOperation
    -0.64
     AROUND
    -0.63
     africaine
    -0.63
    StoryboardSegue
    -0.63
     BoxDecoration
    -0.62
     Around
    -0.62
    ArrowToggle
    -0.58
    POSITIVE LOGITS
     it
    0.72
     there
    0.50
    Erfolge
    0.49
    âmetros
    0.47
     the
    0.47
     you
    0.47
    Външни
    0.46
    atility
    0.46
     Prince
    0.45
    Extinguishing
    0.45
    Activations Density 0.602%

    No Known Activations