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. 74116
    Prev
    Next
    INDEX
    Explanations

    broadening

    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
     you
    -1.67
    you
    -1.48
    You
    -1.33
     You
    -1.32
     YOU
    -1.16
    YOU
    -1.16
    您
    -1.11
    você
    -1.09
    your
    -1.09
     we
    -1.07
    POSITIVE LOGITS
     he
    0.47
    remia
    0.38
    bitset
    0.36
    newtheorem
    0.35
    érie
    0.35
    inheritDoc
    0.35
    ">{{
    0.35
    inyl
    0.34
     Pringle
    0.34
    iver
    0.34
    Activations Density 0.002%

    No Known Activations