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. 20-CLT-HP
    4. 74098
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · 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
    usy
    -0.48
    chenen
    -0.47
    glass
    -0.45
     Filled
    -0.45
    compañ
    -0.44
     usine
    -0.43
    halb
    -0.43
     glass
    -0.42
     udaler
    -0.41
     pcs
    -0.41
    POSITIVE LOGITS
    Obrázky
    0.62
    NewReader
    0.60
    UnknownFields
    0.59
    RegistryLite
    0.59
    mybatisplus
    0.55
    RetentionPolicy
    0.53
     doInBackground
    0.52
    الحياه
    0.52
    scriptcase
    0.51
    GeoNames
    0.50
    Activations Density 0.000%

    No Known Activations