© 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. 4579
    Prev
    Next
    INDEX
    Explanations

    would

    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>
    -1.01
     متعلقه
    -0.52
     justiça
    -0.47
     remarkable
    -0.47
     Normdatei
    -0.45
     cél
    -0.44
     svært
    -0.44
     esperti
    -0.44
     kepad
    -0.44
     enigmatic
    -0.44
    POSITIVE LOGITS
    WebVitals
    0.79
     дописавши
    0.69
    ValueGenerated
    0.68
     Мексичка
    0.63
    Rüyada
    0.59
     Orrell
    0.58
    ighed
    0.57
    \}\\
    0.56
     endfor
    0.56
    Condol
    0.56
    Activations Density 0.028%

    No Known Activations