© 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. 71544
    Prev
    Next
    INDEX
    Explanations

    Code and reports

    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
    Personensuche
    -0.77
    Билгалдахарш
    -0.75
    estacks
    -0.74
    dafx
    -0.74
     Cassini
    -0.74
    WaitGroup
    -0.73
    +#+#
    -0.71
    FormTagHelper
    -0.71
     poffe
    -0.71
    findpost
    -0.70
    POSITIVE LOGITS
    tdessen
    0.46
     venuto
    0.41
    angliski
    0.40
     randonnée
    0.39
    nola
    0.38
     Turquie
    0.38
    lioni
    0.37
    fired
    0.36
     ddelweddau
    0.36
     viento
    0.36
    Activations Density 0.000%

    No Known Activations