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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74265
    Prev
    Next
    INDEX
    Explanations

    against

    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
     "..\..\
    -0.67
     سكانية
    -0.56
     "..\..\..\
    -0.55
    agisse
    -0.54
    iastes
    -0.52
    __":
    
    -0.52
    ResumeLayout
    -0.50
    '):
    
    -0.50
    SequentialGroup
    -0.49
    }")
    
    -0.46
    POSITIVE LOGITS
    RenderAtEndOf
    0.67
    Datuak
    0.66
    ConstraintMaker
    0.64
    ècie
    0.63
     Мексичка
    0.62
     урна
    0.60
    MigrationBuilder
    0.59
     BoxFit
    0.55
    COUVER
    0.55
     للمعارف
    0.53
    Activations Density 0.001%

    No Known Activations