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. 74607
    Prev
    Next
    INDEX
    Explanations

    periods

    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
     she
    -1.62
     he
    -1.58
     our
    -1.52
     they
    -1.48
     we
    -1.41
     you
    -1.21
    He
    -1.20
    She
    -1.04
    they
    -0.97
     nosso
    -0.97
    POSITIVE LOGITS
     We
    0.91
     iprot
    0.52
    MergeFrom
    0.52
    ⓘ
    0.52
    IndentedString
    0.51
     незавершена
    0.50
    $\%
    0.49
    исленность
    0.49
     hefyd
    0.48
    tolsó
    0.48
    Activations Density 0.067%

    No Known Activations