© 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. 78143
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Normdatei
    -0.60
     existing
    -0.54
    currentColor
    -0.51
     AppColors
    -0.49
    niad
    -0.49
     current
    -0.49
    NameInMap
    -0.49
    ROMA
    -0.49
     forwarding
    -0.48
    UrlResolution
    -0.47
    POSITIVE LOGITS
     propOrder
    0.57
     saites
    0.52
    Билгалдахарш
    0.50
    FieldBuilder
    0.50
     naik
    0.50
     AssemblyTitle
    0.49
     protoimpl
    0.48
    Traceback
    0.47
    SequentialGroup
    0.47
    öße
    0.46
    Activations Density 0.000%

    No Known Activations