Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97984
    Prev
    Next
    INDEX
    Explanations

    formal descriptions

    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
    !("{}",
    -0.59
    imon
    -0.49
    jiang
    -0.47
     DJ
    -0.47
    éda
    -0.46
     Objek
    -0.45
    ::*;
    -0.44
     Imp
    -0.43
    Portail
    -0.43
     Ron
    -0.42
    POSITIVE LOGITS
    awtextra
    0.90
     ProtoMessage
    0.77
     rhestr
    0.76
    Jeografia
    0.73
     propOrder
    0.73
     initComponents
    0.71
     HttpHeaders
    0.71
    oredCriteria
    0.71
     Vrbo
    0.70
     CreateTagHelper
    0.70
    Activations Density 2.227%

    No Known Activations