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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44318
    Prev
    Next
    INDEX
    Explanations

    Article and stories

    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
    ReusableCell
    -0.70
    *}
    
    -0.69
    RegressionTest
    -0.69
     myſelf
    -0.69
     RIPRODUZIONE
    -0.68
    OGND
    -0.67
     guère
    -0.66
    )";
    
    -0.64
    "},
    
    -0.64
     rayures
    -0.61
    POSITIVE LOGITS
     of
    0.68
    ches
    0.57
    fully
    0.54
    Tikang
    0.53
     points
    0.52
    ting
    0.51
    an
    0.50
    Tracce
    0.49
    points
    0.48
    PRNewswire
    0.48
    Activations Density 0.116%

    No Known Activations