© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1952
    Prev
    Next
    INDEX
    Explanations

    SQL "JOIN" command

    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
     IndexPath
    -0.67
    UrlResolution
    -0.61
    AddTagHelper
    -0.60
    ContentAsync
    -0.59
    PasswordField
    -0.54
    <?
    -0.54
    /*
    -0.52
    seye
    -0.52
     насељу
    -0.52
    psack
    -0.51
    POSITIVE LOGITS
    허
    0.56
    Naissance
    0.56
    mán
    0.53
     kasarigan
    0.49
     Hyman
    0.45
     weg
    0.45
     considérons
    0.45
    freies
    0.45
    ation
    0.44
     rät
    0.44
    Activations Density 0.012%

    No Known Activations