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. 11161
    Prev
    Next
    INDEX
    Explanations

    new

    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
    \{\\
    -0.66
    ?>">
    -0.54
    UserScript
    -0.53
     gäller
    -0.52
     Meksiko
    -0.52
     thereto
    -0.51
     normaux
    -0.50
     تجاه
    -0.50
     oraș
    -0.50
    setProgress
    -0.49
    POSITIVE LOGITS
     ujednoznacz
    0.58
    XmlAccessorType
    0.57
    ClCompile
    0.56
     CommandType
    0.56
    Vidite
    0.54
     Treaty
    0.53
    примеча
    0.52
     AssemblyCulture
    0.52
    expandindo
    0.51
    bė
    0.51
    Activations Density 0.015%

    No Known Activations