© 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. 6049
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    yntaxException
    -0.63
     المعيارى
    -0.59
    Espèce
    -0.53
     trasparente
    -0.52
     AttributeError
    -0.51
    cshtml
    -0.50
    AlterField
    -0.50
    TagHelper
    -0.50
     gäller
    -0.50
     <>",
    -0.50
    POSITIVE LOGITS
     postIndex
    0.69
     onOptions
    0.56
    tonsoft
    0.54
     wealth
    0.54
     bounty
    0.53
     nahilalakip
    0.53
    >//
    0.50
     titles
    0.48
     endowments
    0.47
     endowment
    0.47
    Activations Density 0.002%

    No Known Activations