© 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. 5-CLT-HP
    7. 6063
    Prev
    Next
    INDEX
    Explanations

    consideration

    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
     the
    -0.77
     your
    -0.63
     a
    -0.56
     his
    -0.51
    migrationBuilder
    -0.50
    ِّف
    -0.48
     cuán
    -0.47
    tainers
    -0.47
     whether
    -0.47
    coming
    -0.46
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.70
     before
    0.66
    Παραπομπές
    0.63
     sebelum
    0.58
    országban
    0.55
     tartalomajánló
    0.55
     juridiques
    0.55
     innan
    0.54
     déclarations
    0.54
    abestanden
    0.53
    Activations Density 0.001%

    No Known Activations