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. 74332
    Prev
    Next
    INDEX
    Explanations

    Memory

    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
    :✨
    -0.82
    ragalactic
    -0.74
    CodedInputStream
    -0.70
    цездатний
    -0.70
     propOrder
    -0.66
    Zeneca
    -0.65
    HasAnnotation
    -0.64
    gdala
    -0.63
    endregion
    -0.63
    Personendaten
    -0.62
    POSITIVE LOGITS
     type
    0.47
     need
    0.46
    GOTREF
    0.46
     takes
    0.46
     Takes
    0.45
     Ern
    0.43
    ophores
    0.43
    ophore
    0.42
    forName
    0.42
    moveToNext
    0.42
    Activations Density 0.029%

    No Known Activations