© 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. 78175
    Prev
    Next
    INDEX
    Explanations

    Code and documentation

    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
     Lázaro
    -0.60
     Neale
    -0.53
     pinball
    -0.53
     Heuer
    -0.52
     Khor
    -0.52
    setWindow
    -0.52
     Grinder
    -0.52
     tachy
    -0.51
     Económica
    -0.50
    orki
    -0.50
    POSITIVE LOGITS
     R
    0.65
    MessageOf
    0.60
     OMIT
    0.55
    ✭
    0.55
    Geplaatst
    0.55
    ArrowToggle
    0.55
    BASEPATH
    0.54
    setVerticalGroup
    0.52
     MessageBoxIcon
    0.52
    R
    0.51
    Activations Density 0.001%

    No Known Activations