© 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. 4784
    Prev
    Next
    INDEX
    Explanations

    Joined by

    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
    fromnode
    -0.54
    arder
    -0.52
    FormTagHelper
    -0.51
     <<<<<<<<<<<<<<
    -0.51
     authService
    -0.50
    Gambas
    -0.50
    יח
    -0.50
     벡터
    -0.49
    mybatisplus
    -0.49
     vettor
    -0.48
    POSITIVE LOGITS
     additional
    0.57
     others
    0.57
     other
    0.56
    AddHtmlAttribute
    0.55
    lotl
    0.53
    ularis
    0.51
    льевич
    0.51
     autres
    0.51
     entered
    0.51
    Otras
    0.51
    Activations Density 0.002%

    No Known Activations