© 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. 20-CLT-HP
    7. 76830
    Prev
    Next
    INDEX
    Explanations

    Computer code and testing

    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
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.79
    Viited
    -0.76
     Савезне
    -0.73
     onPostExecute
    -0.72
    ыгана
    -0.71
     linkovi
    -0.68
     CreateTagHelper
    -0.68
    الحياه
    -0.67
    Jeografia
    -0.66
    зулта
    -0.66
    POSITIVE LOGITS
    enumi
    0.61
     gets
    0.54
     helps
    0.53
     referenties
    0.53
     holds
    0.45
     tells
    0.45
     wakes
    0.44
     Bra
    0.42
    gets
    0.42
     Gets
    0.42
    Activations Density 0.001%

    No Known Activations