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. 97898
    Prev
    Next
    INDEX
    Explanations

    scientist

    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
    IntoConstraints
    -0.92
     BoxFit
    -0.92
     scientist
    -0.84
    
    -0.82
    parian
    -0.81
     GenerationType
    -0.79
    SBATCH
    -0.78
    +#+#
    -0.77
     scientifique
    -0.75
    IVEREF
    -0.74
    POSITIVE LOGITS
    ous
    0.47
    als
    0.46
    ly
    0.44
    less
    0.42
     ters
    0.40
     output
    0.39
    s
    0.39
    лян
    0.38
    al
    0.38
    ль
    0.37
    Activations Density 0.105%

    No Known Activations