© 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. 1-CLT-HP
    7. 8644
    Prev
    Next
    INDEX
    Explanations

    in

    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
    Negative Logits
    no
    -0.57
    TestFixture
    -0.53
     الرياضيه
    -0.52
    atste
    -0.51
     étant
    -0.49
    Using
    -0.49
     suivants
    -0.48
     Вікіпе
    -0.48
    abus
    -0.48
     šk
    -0.47
    POSITIVE LOGITS
    sizeCache
    0.86
    BeginContext
    0.76
     AttributeSet
    0.68
    Autoritní
    0.64
    ParallelGroup
    0.60
     strconv
    0.57
    #+#
    0.57
    IsPostBack
    0.57
    новништво
    0.57
     and
    0.56
    Activations Density 0.015%

    No Known Activations