© 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. 10131
    Prev
    Next
    INDEX
    Explanations

    dog

    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
     dogs
    -1.05
     Dogs
    -1.02
     DOGS
    -0.94
     dog
    -0.93
     DOG
    -0.91
     Dog
    -0.86
    Dogs
    -0.85
    dog
    -0.84
    Dog
    -0.83
    dogs
    -0.79
    POSITIVE LOGITS
    myModal
    0.55
    วัส
    0.55
    invokeLater
    0.54
    loem
    0.51
     FormsModule
    0.50
    slee
    0.48
    ophan
    0.48
     BoxDecoration
    0.48
    Shh
    0.47
    essentiel
    0.46
    Activations Density 0.012%

    No Known Activations