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. 74273
    Prev
    Next
    INDEX
    Explanations

    Formal passages

    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
     חיצוניים
    -0.75
     Jefus
    -0.74
     Monfieur
    -0.73
     Theſe
    -0.70
     Anſ
    -0.70
     protoimpl
    -0.69
     typelib
    -0.69
    httphttps
    -0.69
    onAttach
    -0.68
    ^(@)
    -0.67
    POSITIVE LOGITS
     high
    0.62
     hurt
    0.60
     w
    0.57
     care
    0.54
     pul
    0.54
    GOTREF
    0.51
     wa
    0.48
     against
    0.47
    high
    0.47
     hoge
    0.47
    Activations Density 0.006%

    No Known Activations