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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16308
    Prev
    Next
    INDEX
    Explanations

    Java code relating to setting and getting player attributes such as handedness, runs scored, strike rate, etc

    oai_token-act-pair · gemini-2.0-flash

    Java code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.74
     dafs
    -0.72
     bezeichneter
    -0.72
     Bourgoin
    -0.67
     Monfieur
    -0.67
     tfsi
    -0.66
     ſche
    -0.65
    )++;
    -0.65
     faſt
    -0.65
     dieß
    -0.64
    POSITIVE LOGITS
    pageX
    0.48
    будь
    0.47
    länd
    0.43
     snippetHide
    0.43
     ar
    0.42
    Välislingid
    0.41
     spieg
    0.41
    setCellStyle
    0.40
     assolu
    0.40
    mainloop
    0.40
    Activations Density 0.495%

    No Known Activations