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. 1-CLT-HP
    4. 11239
    Prev
    Next
    INDEX
    Explanations

    placement, situation

    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
     an
    -0.68
     a
    -0.66
     the
    -0.64
    quiel
    -0.59
     it
    -0.54
     du
    -0.54
     your
    -0.52
     all
    -0.52
     Frank
    -0.52
     what
    -0.51
    POSITIVE LOGITS
     myſelf
    0.74
     parlé
    0.70
     aidé
    0.68
    eraard
    0.66
     refusé
    0.66
     canina
    0.64
     contribué
    0.64
     longtemps
    0.64
    GetEnumerator
    0.64
     parlant
    0.63
    Activations Density 0.526%

    No Known Activations