© 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. 1-CLT-HP
    7. 45755
    Prev
    Next
    INDEX
    Explanations

    down

    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
    jsxFileName
    -0.56
    
    -0.56
     jLabel
    -0.54
    SBATCH
    -0.51
     jScrollPane
    -0.50
     MediatR
    -0.49
     viewDidLoad
    -0.48
    astéroïdes
    -0.48
     AttributeSet
    -0.46
    nodoc
    -0.45
    POSITIVE LOGITS
     Infórmanos
    0.60
    paž
    0.57
     upo
    0.56
     الأصل
    0.54
     pescoço
    0.54
     aught
    0.53
    SharedDtor
    0.52
     afresh
    0.52
    Background
    0.51
    BeforeEach
    0.50
    Activations Density 0.006%

    No Known Activations