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. 0-CLT-HP
    4. 519
    Prev
    Next
    INDEX
    Explanations

    kind or type

    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
     where
    -0.49
     as
    -0.49
    where
    -0.45
     sted
    -0.45
     and
    -0.44
    o
    -0.44
     points
    -0.42
    point
    -0.41
    y
    -0.41
     on
    -0.40
    POSITIVE LOGITS
     AssemblyCulture
    1.07
    \{\\
    1.02
     nahilalakip
    0.98
    Personendaten
    0.96
    ंदीखरीदारी
    0.92
    出版年
    0.91
     يتيمه
    0.90
     jScrollPane
    0.90
     Chwiliwch
    0.88
    __":
    
    0.82
    Activations Density 0.369%

    No Known Activations