© 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. 4436
    Prev
    Next
    INDEX
    Explanations

    leadership

    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
     utafitiHapana
    -0.61
    cabul
    -0.60
    SizeF
    -0.59
    
    -0.56
    GraphicsUnit
    -0.54
    Tikang
    -0.54
    LoadScene
    -0.54
    unding
    -0.53
    <table>
    -0.51
    matous
    -0.50
    POSITIVE LOGITS
     qualities
    0.69
     Qualities
    0.60
     quality
    0.60
     qualités
    0.56
    complexContent
    0.56
    :+:
    0.55
    CrossRef
    0.53
     qualità
    0.52
    azgo
    0.52
    Stellar
    0.50
    Activations Density 0.002%

    No Known Activations