© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97681
    Prev
    Next
    INDEX
    Explanations

    expert advice/frameworks

    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
     experts
    -1.23
    experts
    -1.14
    Experts
    -1.10
     Experts
    -1.02
     expertos
    -0.86
     esperti
    -0.82
     expert
    -0.81
    expert
    -0.81
    };*/
    -0.80
     EXPERT
    -0.77
    POSITIVE LOGITS
     résister
    0.51
    zene
    0.49
     sár
    0.47
     défendre
    0.47
     such
    0.44
    zucht
    0.43
     proudest
    0.43
    ố
    0.42
     sej
    0.42
     honneur
    0.42
    Activations Density 1.277%

    No Known Activations