© 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. 0-CLT-HP
    7. 43962
    Prev
    Next
    INDEX
    Explanations

    header

    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
     header
    -0.75
    labeled
    -0.75
     label
    -0.65
    HEADER
    -0.61
    header
    -0.58
    labelled
    -0.54
     headers
    -0.51
     Header
    -0.51
    label
    -0.50
    Header
    -0.45
    POSITIVE LOGITS
    DeleteBehavior
    1.04
    DockStyle
    1.00
    fjspx
    0.96
    ArrowToggle
    0.95
     дописавши
    0.93
    sizeCache
    0.92
    elemField
    0.92
    SharedDtor
    0.90
    yntaxException
    0.90
    IndentedString
    0.90
    Activations Density 0.121%

    No Known Activations