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. 1-CLT-HP
    4. 11264
    Prev
    Next
    INDEX
    Explanations

    trans

    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
     trans
    -0.87
    <bos>
    -0.84
     Trans
    -0.69
    TRANS
    -0.60
    trans
    -0.60
    Trans
    -0.59
     TRANS
    -0.58
     tranſ
    -0.58
     merging
    -0.52
     CreateTagHelper
    -0.52
    POSITIVE LOGITS
     متعلقه
    0.56
    ContentAsync
    0.54
    ReusableCell
    0.50
    writeFieldEnd
    0.49
    chyma
    0.48
    UrlResolution
    0.47
    lob
    0.47
    chitz
    0.46
    fjspx
    0.46
    HasColumnType
    0.45
    Activations Density 0.097%

    No Known Activations