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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73840
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    tagHelperRunner
    -0.83
    RectangleBorder
    -0.71
    sizeCache
    -0.66
    alyptus
    -0.65
     nargin
    -0.64
    లాలు
    -0.63
    __":
    
    -0.63
    SharedDtor
    -0.62
    keyColumn
    -0.62
    riwal
    -0.62
    POSITIVE LOGITS
     termo
    0.43
    DoubleQuotes
    0.40
    PasswordEncoder
    0.39
     nu
    0.37
    Ns
    0.37
    NS
    0.36
     Total
    0.36
    NU
    0.35
    anty
    0.35
    LayoutStyle
    0.34
    Activations Density 0.004%

    No Known Activations