© 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. 12359
    Prev
    Next
    INDEX
    Explanations

    write

    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
    interopRequire
    -0.84
    setVerticalGroup
    -0.78
    ScopeManager
    -0.68
    ########.
    -0.68
    RegistryLite
    -0.67
    ⓧ
    -0.66
    contentLoaded
    -0.65
    reportWebVitals
    -0.65
     AspNetCore
    -0.64
    Datuak
    -0.63
    POSITIVE LOGITS
     to
    0.51
     area
    0.43
    v
    0.42
    1
    0.42
     vs
    0.42
    2
    0.40
    dega
    0.40
     s
    0.40
     
    0.40
     rospy
    0.39
    Activations Density 0.358%

    No Known Activations