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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13983
    Prev
    Next
    INDEX
    Explanations

    it

    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
     
    -0.73
    ↵
    -0.68
    ↵↵
    -0.63
    <eos>
    -0.59
     in
    -0.57
      
    -0.52
     as
    -0.51
     and
    -0.50
     $
    -0.50
     (
    -0.49
    POSITIVE LOGITS
     nakalista
    1.77
     myſelf
    1.74
    Personensuche
    1.70
     itſelf
    1.66
    MigrationBuilder
    1.66
     Monfieur
    1.61
     Efq
    1.59
     Мексичка
    1.59
     Majefty
    1.59
     pleaſure
    1.58
    Activations Density 0.023%

    No Known Activations