© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78094
    Prev
    Next
    INDEX
    Explanations

    Mixed sources, disparate content

    np_max-act-logits · 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
    Negative Logits
    webElementXpaths
    -0.63
    inā
    -0.56
    GEBURTSDATUM
    -0.54
    sphase
    -0.53
     Vordergrund
    -0.53
    lwjgl
    -0.51
    AddTagHelper
    -0.50
     onBind
    -0.49
     '-':
    -0.49
    ädie
    -0.49
    POSITIVE LOGITS
     &___
    0.54
    RTEE
    0.50
    +#+#
    0.48
     []:
    0.47
    حياته
    0.47
     disambiguazione
    0.47
    ætter
    0.47
     AssemblyCulture
    0.45
    ValueStyle
    0.45
     متعلقه
    0.45
    Activations Density 0.000%

    No Known Activations