© 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. 12353
    Prev
    Next
    INDEX
    Explanations

    Islam

    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
    <bos>
    -1.17
     AssemblyTitle
    -0.72
     المعيارى
    -0.67
    }`).
    -0.67
    AndEndTag
    -0.66
    Autoritní
    -0.66
     GenerationType
    -0.64
     Morde
    -0.56
    تقاوى
    -0.56
     AssemblyCompany
    -0.56
    POSITIVE LOGITS
     picioare
    0.63
     básicas
    0.55
    pill
    0.53
     vœux
    0.53
     combinação
    0.52
    ennemi
    0.50
     rând
    0.50
     mariée
    0.48
     argint
    0.48
     consectetur
    0.48
    Activations Density 0.020%

    No Known Activations