© 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. 91186
    Prev
    Next
    INDEX
    Explanations

    groupings

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Niños
    -0.48
    inden
    -0.44
    oin
    -0.43
     Kien
    -0.42
    nias
    -0.41
    mere
    -0.41
     Or
    -0.41
    Rég
    -0.41
     Rég
    -0.41
    inin
    -0.41
    POSITIVE LOGITS
    BeginContext
    0.87
    AndEndTag
    0.85
    
    0.84
     autorytatywna
    0.78
    setVerticalGroup
    0.78
    IntoConstraints
    0.77
     CreateTagHelper
    0.76
    ContentAsync
    0.74
     AssemblyVersion
    0.72
    новништво
    0.71
    Activations Density 0.002%

    No Known Activations