© 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. 4-CLT-HP
    7. 3371
    Prev
    Next
    INDEX
    Explanations

    percent

    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
     ThemeData
    -0.64
    RUnlock
    -0.61
    didSet
    -0.55
    ########.
    -0.53
    tvguidetime
    -0.53
    invokeLater
    -0.52
     CSM
    -0.51
    IMPORTED
    -0.51
     soigne
    -0.50
     lontano
    -0.50
    POSITIVE LOGITS
     Cox
    0.57
    ziek
    0.55
     Student
    0.51
    zahn
    0.50
     Mode
    0.50
    словно
    0.49
    aik
    0.49
     Tra
    0.48
     mode
    0.48
    oprene
    0.47
    Activations Density 0.002%

    No Known Activations