© 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. 4425
    Prev
    Next
    INDEX
    Explanations

    тому

    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
     ainfi
    -1.17
     femininas
    -1.14
     igång
    -1.13
     femininos
    -1.12
     varandra
    -1.12
     démocr
    -1.11
     vermelhas
    -1.09
     chré
    -1.08
     réguli
    -1.07
     vägen
    -1.06
    POSITIVE LOGITS
     fra
    0.63
     pol
    0.60
    ’
    0.60
     pa
    0.58
     par
    0.56
     ta
    0.56
     ses
    0.56
     Ce
    0.56
      
    0.55
     ma
    0.55
    Activations Density 0.203%

    No Known Activations