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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14187
    Prev
    Next
    INDEX
    Explanations

    Java

    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
     Java
    -1.25
     JAVA
    -0.91
    Java
    -0.90
     java
    -0.85
     Javan
    -0.73
    JAVA
    -0.68
    java
    -0.62
     Sumatra
    -0.53
     Jawa
    -0.52
     Roskov
    -0.51
    POSITIVE LOGITS
    SetString
    0.58
     صوتيه
    0.57
     Index
    0.56
    EC
    0.55
     External
    0.54
    lexikon
    0.54
     sidan
    0.53
     SKE
    0.52
     "..\..\
    0.52
     hôtes
    0.52
    Activations Density 0.023%

    No Known Activations