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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74221
    Prev
    Next
    INDEX
    Explanations

    software development

    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
     disponibilités
    -0.54
    plates
    -0.50
    gapan
    -0.47
    τυχ
    -0.47
    StandardCharsets
    -0.47
    codes
    -0.46
    RegistryLite
    -0.46
     plates
    -0.43
     JScrollPane
    -0.43
    codegen
    -0.43
    POSITIVE LOGITS
    MLLoader
    0.67
    ьаж
    0.56
     blended
    0.56
     IBOutlet
    0.56
    neum
    0.55
    KURZBESCHREIBUNG
    0.54
    CPtr
    0.54
    twimg
    0.52
     كومونز
    0.52
     تانيه
    0.50
    Activations Density 0.001%

    No Known Activations