© 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. 9463
    Prev
    Next
    INDEX
    Explanations

    period

    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
     Audiodateien
    -0.72
     albedo
    -0.66
     sterilization
    -0.66
    ergies
    -0.63
     cyclones
    -0.63
     centrifug
    -0.62
    yntaxException
    -0.61
     дописавши
    -0.60
     centrifugation
    -0.59
     caldera
    -0.59
    POSITIVE LOGITS
     of
    0.74
     CreateTagHelper
    0.63
    rungsseite
    0.53
    ForRow
    0.48
    old
    0.47
     createState
    0.46
     Old
    0.45
     leading
    0.45
     old
    0.44
     του
    0.43
    Activations Density 0.002%

    No Known Activations