© 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. 2878
    Prev
    Next
    INDEX
    Explanations

    input

    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
     hist
    -0.53
    ADP
    -0.47
     stick
    -0.46
     darbu
    -0.45
    BASELINE
    -0.41
    Endereço
    -0.41
    TOP
    -0.41
     lean
    -0.40
    ַע
    -0.40
    PPP
    -0.40
    POSITIVE LOGITS
     ProtoMessage
    0.85
    AndEndTag
    0.62
    TagMode
    0.61
     समीक्षाओं
    0.60
     nahilalakip
    0.60
    tanleria
    0.59
    InjectAttribute
    0.59
    الحياه
    0.57
     ujednoznacz
    0.57
     defaultstate
    0.57
    Activations Density 0.003%

    No Known Activations