© 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. 0-CLT-HP
    7. 94723
    Prev
    Next
    INDEX
    Explanations

    improvements and positive developments

    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
     flourished
    -1.05
     flourish
    -1.00
    InputBorder
    -0.96
    RectangleBorder
    -0.94
     thrived
    -0.94
     prosperity
    -0.94
     prosperous
    -0.91
     proficiency
    -0.91
     thrive
    -0.90
     snippetHide
    -0.90
    POSITIVE LOGITS
     á
    0.47
     in
    0.47
    loca
    0.44
     and
    0.43
     so
    0.40
    ,
    0.40
     sur
    0.39
     under
    0.39
     qu
    0.38
     lat
    0.38
    Activations Density 0.096%

    No Known Activations