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. 0-CLT-HP
    4. 2
    Prev
    Next
    INDEX
    Explanations

    macbook

    np_max-act · 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
    mores
    -2.41
    more
    -1.05
     more
    -1.04
    Geplaatst
    -0.85
    More
    -0.81
    MORE
    -0.81
     mores
    -0.78
     MORE
    -0.77
    .*")]
    -0.76
     lebih
    -0.76
    POSITIVE LOGITS
    eche
    0.56
    saraba
    0.56
     or
    0.52
    enzio
    0.49
     otherwise
    0.49
    ponge
    0.47
    ldo
    0.46
     Craig
    0.46
     Dauer
    0.46
     avanti
    0.45
    Activations Density 0.656%

    No Known Activations