© 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. 16023
    Prev
    Next
    INDEX
    Explanations

    chemistry/physics

    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
    ing
    -0.77
    y
    -0.64
    ة
    -0.57
    a
    -0.54
    adi
    -0.53
     Physic
    -0.53
    βα
    -0.50
    as
    -0.47
    o
    -0.47
    an
    -0.47
    POSITIVE LOGITS
    SSF
    0.68
    NOPQRST
    0.63
    extAlignment
    0.62
     numberWith
    0.59
    ochemical
    0.59
     Majest
    0.59
     SqlCommand
    0.57
     Signalez
    0.57
     وتسجيلات
    0.57
     ISTAT
    0.56
    Activations Density 0.007%

    No Known Activations