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. 11235
    Prev
    Next
    INDEX
    Explanations

    obo

    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
    FieldBuilder
    -0.64
    apon
    -0.57
    شهاد
    -0.56
    doria
    -0.55
    mbad
    -0.55
    BufferException
    -0.55
     AssemblyProduct
    -0.54
    itania
    -0.54
     pictorial
    -0.54
    ])):
    -0.54
    POSITIVE LOGITS
    ꒳
    0.54
     cipolla
    0.52
    sigue
    0.49
    Portail
    0.47
     lleno
    0.45
    setVerticalGroup
    0.45
     للاسماء
    0.44
     sitten
    0.44
    Washington
    0.43
    fjspx
    0.43
    Activations Density 0.061%

    No Known Activations