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. 74580
    Prev
    Next
    INDEX
    Explanations

    )

    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
     AssemblyCulture
    -0.71
    AnimationsModule
    -0.66
     >=",
    -0.64
     nhàng
    -0.57
     Svar
    -0.56
    numerusform
    -0.53
    HasForeignKey
    -0.53
     linkovi
    -0.52
     '\\;'
    -0.51
     &___
    -0.51
    POSITIVE LOGITS
    BER
    0.58
     PeEnEo
    0.54
    ber
    0.54
    曖昧さ回避
    0.50
     Be
    0.49
    BE
    0.47
    StoryboardSegue
    0.47
    UniformLocation
    0.46
    Be
    0.45
    afficheront
    0.45
    Activations Density 0.028%

    No Known Activations