© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13671
    Prev
    Next
    INDEX
    Explanations

    animals, play, glass, name

    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
     canine
    -1.13
     Canine
    -1.05
    dogs
    -0.68
    n
    -0.63
    ton
    -0.63
     umane
    -0.62
    name
    -0.61
     nonatomic
    -0.60
     humanas
    -0.60
    human
    -0.59
    POSITIVE LOGITS
     متعلقه
    0.55
    ंदीखरीदारी
    0.53
     InputDecoration
    0.52
    Autoritní
    0.52
     OMR
    0.49
     ddelweddau
    0.48
    hdashline
    0.47
     समीक्षक
    0.47
    NewLabel
    0.47
     &___
    0.47
    Activations Density 0.038%

    No Known Activations