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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 46264
    Prev
    Next
    INDEX
    Explanations

    ur

    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
    er
    -0.65
     ModelExpression
    -0.63
    webElementXpaths
    -0.56
     Miss
    -0.52
     Normdatei
    -0.51
     CreateTagHelper
    -0.49
     perm
    -0.47
    ις
    -0.47
     fact
    -0.46
    InjectAttribute
    -0.46
    POSITIVE LOGITS
    </caption>
    0.59
    pyplot
    0.58
    MENAFN
    0.56
     PrintWriter
    0.54
    بوابة
    0.54
    paramInt
    0.53
     pyplot
    0.52
    ھا
    0.52
    enschappe
    0.50
    Indep
    0.50
    Activations Density 0.021%

    No Known Activations