© 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. 3101
    Prev
    Next
    INDEX
    Explanations

    even

    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
    TagHelper
    -0.56
    textTheme
    -0.55
    UpInside
    -0.55
     Zah
    -0.54
     AppModule
    -0.54
     متعلقه
    -0.53
     anticoag
    -0.53
     naming
    -0.52
    GRAPHY
    -0.52
     defaultstate
    -0.52
    POSITIVE LOGITS
    GOTREF
    0.57
     definitely
    0.48
    AndEndTag
    0.47
     assolutamente
    0.46
    forKey
    0.45
    Close
    0.45
     herum
    0.44
     ruinas
    0.44
    Fid
    0.43
     sicuramente
    0.43
    Activations Density 0.003%

    No Known Activations