© 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. 1-CLT-HP
    7. 8782
    Prev
    Next
    INDEX
    Explanations

    Questions and suggestions

    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
    Negative Logits
     idea
    -0.98
    idea
    -0.88
    Idea
    -0.88
     concept
    -0.88
     idee
    -0.84
     idée
    -0.83
     ideas
    -0.82
     Idea
    -0.82
    Ideas
    -0.82
     idées
    -0.79
    POSITIVE LOGITS
     FetchType
    0.71
     noDo
    0.65
    AddTagHelper
    0.64
    findpost
    0.63
    UnusedPrivate
    0.62
     Infórmanos
    0.60
    /*
    0.59
     समीक्षक
    0.59
     Daarna
    0.58
     Meksiku
    0.58
    Activations Density 0.014%

    No Known Activations