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. 20-CLT-HP
    4. 74034
    Prev
    Next
    INDEX
    Explanations

    Bas

    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
     Efq
    -0.48
     Например
    -0.47
     Drapeau
    -0.47
     ſta
    -0.46
     ſch
    -0.46
     myſelf
    -0.46
     ſte
    -0.45
    ponses
    -0.45
    cology
    -0.44
    setLayoutManager
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.85
     EconPapers
    0.60
     Chwiliwch
    0.59
    GEBURTSDATUM
    0.56
    клопе
    0.55
     nakalista
    0.55
    oa̍t
    0.54
    Insn
    0.54
    +#+#
    0.53
    ymce
    0.51
    Activations Density 0.001%

    No Known Activations