© 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. 12384
    Prev
    Next
    INDEX
    Explanations

    make

    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
     متعلقه
    -0.69
    ValueStyle
    -0.59
    Personendaten
    -0.59
     bezeichneter
    -0.57
    rogly
    -0.52
    opathic
    -0.51
     polys
    -0.50
     uncin
    -0.50
     sclerosis
    -0.50
    Iden
    -0.49
    POSITIVE LOGITS
     vectorielles
    0.60
    FailureListener
    0.58
    apimachinery
    0.57
    routeProvider
    0.56
    TagHelper
    0.56
    ambilan
    0.55
    ddots
    0.54
     collègues
    0.52
     composants
    0.52
     kehidupan
    0.52
    Activations Density 0.017%

    No Known Activations