Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74023
    Prev
    Next
    INDEX
    Explanations

    Code and news

    np_max-act-logits · 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
     الحره
    -0.75
     الرياضيه
    -0.65
     ddelweddau
    -0.58
    WriteBarrier
    -0.54
     GenerationType
    -0.53
    IonicModule
    -0.51
    المناصب
    -0.51
    CloseOperation
    -0.51
    writeFieldEnd
    -0.49
     المعيارى
    -0.49
    POSITIVE LOGITS
     Go
    0.67
    Go
    0.66
     Huns
    0.53
     getCode
    0.52
    Bars
    0.51
    Expose
    0.51
     conscientes
    0.51
     braccia
    0.50
    OGND
    0.50
    ulties
    0.50
    Activations Density 0.000%

    No Known Activations