Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74489
    Prev
    Next
    INDEX
    Explanations

    scientific/geographical topics

    np_max-act-logits · 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
     myſelf
    -1.23
     Efq
    -1.21
     Monfieur
    -1.17
     itſelf
    -1.15
     Jefus
    -1.11
    ſelf
    -1.09
     betweenstory
    -1.09
     becauſe
    -1.07
     themſelves
    -1.06
     Eſ
    -1.05
    POSITIVE LOGITS
    ↵
    0.38
     (
    0.37
    ys
    0.35
      
    0.33
    ↵↵
    0.33
    <eos>
    0.32
    /
    0.32
    +
    0.32
    ung
    0.29
    ,
    0.28
    Activations Density 0.000%

    No Known Activations