© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91435
    Prev
    Next
    INDEX
    Explanations

    Code and special characters

    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
     épreuves
    -0.52
    исленность
    -0.49
    prepareStatement
    -0.48
    chik
    -0.48
     Consumer
    -0.47
    kiat
    -0.47
    RenderAtEndOf
    -0.47
    gatsby
    -0.47
     épreuve
    -0.47
    цездатний
    -0.46
    POSITIVE LOGITS
    IsPostBack
    0.53
    UserScript
    0.52
    ↺
    0.52
    bombs
    0.51
     Bag
    0.51
     snippetHide
    0.50
    ⓧ
    0.50
     InputDecoration
    0.50
     bags
    0.49
     substitutes
    0.49
    Activations Density 0.020%

    No Known Activations