© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12211
    Prev
    Next
    INDEX
    Explanations

    improve

    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
     propOrder
    -0.91
    tagHelperRunner
    -0.78
    MemoryWarning
    -0.73
    oredCriteria
    -0.69
     kaarangay
    -0.66
     الحره
    -0.66
     vuitton
    -0.66
    InjectAttribute
    -0.65
     referenties
    -0.65
    pherals
    -0.65
    POSITIVE LOGITS
    ]--;
    0.55
    WriteTagHelper
    0.50
    '
    0.47
    ]++;
    0.42
    "].
    0.41
    annin
    0.40
    "];
    0.40
    Escuela
    0.39
    [:
    0.38
    ']));
    0.38
    Activations Density 0.175%

    No Known Activations