© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4657
    Prev
    Next
    INDEX
    Explanations

    markup characters

    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
     A
    -0.74
     And
    -0.71
     It
    -0.66
     "
    -0.64
     This
    -0.62
     this
    -0.61
     and
    -0.59
     You
    -0.59
     “
    -0.58
    ↵↵
    -0.57
    POSITIVE LOGITS
     незавершена
    0.69
    soever
    0.68
     ſind
    0.65
     itſelf
    0.65
     allAfrica
    0.65
     mince
    0.64
     שוליים
    0.63
     gynhyrchwyd
    0.63
    
    0.62
    存于互联网档案馆
    0.62
    Activations Density 0.010%

    No Known Activations