© 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. 5-CLT-HP
    7. 1194
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    AnchorTagHelper
    -0.64
    AddTagHelper
    -0.60
    Tembelea
    -0.54
    SpringBootTest
    -0.54
    FundMe
    -0.53
    <?
    -0.52
    ParallelGroup
    -0.51
    textTheme
    -0.51
     zaak
    -0.47
    __":
    -0.47
    POSITIVE LOGITS
    expandindo
    0.69
     متعلقه
    0.69
     FetchType
    0.65
     Biôgrafia
    0.58
     Normdatei
    0.57
    Abit
    0.53
    сылкі
    0.52
     Vision
    0.52
    houd
    0.52
     iprot
    0.52
    Activations Density 0.008%

    No Known Activations