© 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. 5-CLT-HP
    7. 941
    Prev
    Next
    INDEX
    Explanations

    legal/research documents

    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
     חיצוניים
    -0.80
    󠁿
    -0.77
     שוליים
    -0.77
     consultato
    -0.77
     endwhile
    -0.76
     Infórmanos
    -0.73
    PerformLayout
    -0.73
     NIOS
    -0.72
    \{\\
    -0.71
    ReusableCell
    -0.69
    POSITIVE LOGITS
     clause
    0.41
    PTION
    0.39
     rule
    0.38
     Act
    0.37
     fundamental
    0.37
     doctrine
    0.35
     law
    0.35
     standard
    0.35
     Clause
    0.34
     Law
    0.34
    Activations Density 0.008%

    No Known Activations