© 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. 0-CLT-HP
    7. 97676
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    vak
    -0.84
    geable
    -0.75
    iph
    -0.72
    v
    -0.68
    mised
    -0.68
    re
    -0.59
    vard
    -0.59
    gn
    -0.58
    l
    -0.56
     
    -0.56
    POSITIVE LOGITS
     Мексичка
    1.16
    Personensuche
    1.08
     defaultstate
    1.05
    EndGlobalSection
    1.02
    ArrowToggle
    1.02
     fieldNum
    1.00
     MainAxisSize
    0.98
     saites
    0.96
    
    0.96
    SequentialGroup
    0.94
    Activations Density 0.388%

    No Known Activations