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. 74323
    Prev
    Next
    INDEX
    Explanations

    technical documents snippets

    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
     eggs
    -0.93
     Eggs
    -0.90
    Eggs
    -0.83
    eggs
    -0.82
     Eier
    -0.74
    Personensuche
    -0.66
     Apples
    -0.62
     apples
    -0.62
     tickets
    -0.61
    ings
    -0.60
    POSITIVE LOGITS
    AndEndTag
    0.52
    Controllers
    0.50
    ConstraintMaker
    0.45
    HasMaxLength
    0.43
    Serialization
    0.42
    openha
    0.42
    )_/¯
    0.41
    Supervis
    0.41
    LEncoder
    0.40
    popd
    0.40
    Activations Density 0.003%

    No Known Activations