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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1227
    Prev
    Next
    INDEX
    Explanations

    to

    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
    CloseOperation
    -0.66
    ::$_
    -0.62
    mybatisplus
    -0.62
     his
    -0.57
    ergies
    -0.56
     hâte
    -0.56
    ANTLR
    -0.54
     its
    -0.54
     Itself
    -0.53
     magát
    -0.52
    POSITIVE LOGITS
     nahilalakip
    0.60
    новниш
    0.54
     resourceCulture
    0.51
     pinulongan
    0.49
    ppur
    0.48
     and
    0.48
     ComVisible
    0.47
    /**
    0.47
     saites
    0.47
    gand
    0.46
    Activations Density 0.001%

    No Known Activations