© 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. 4-CLT-HP
    7. 4895
    Prev
    Next
    INDEX
    Explanations

    0

    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
     незавершена
    -0.50
     wirkt
    -0.49
    lainen
    -0.48
    newtheorem
    -0.48
    <!--[
    -0.47
    PostExecute
    -0.47
     rangs
    -0.46
     <=",
    -0.45
     للمعارف
    -0.45
    racuse
    -0.45
    POSITIVE LOGITS
     Italijanski
    0.60
    XtraReports
    0.59
    jenner
    0.56
    Clik
    0.56
     mg
    0.55
     mm
    0.55
    الإنجليزية
    0.54
     Biôgrafia
    0.54
    AddTagHelper
    0.54
     trials
    0.53
    Activations Density 0.019%

    No Known Activations