© 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. 5-CLT-HP
    4. 95171
    Prev
    Next
    INDEX
    Explanations

    clear

    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
    "];
    
    -0.88
    "]];
    -0.73
    IntoConstraints
    -0.71
    ."],
    -0.70
     };
    
    -0.70
    ")]
    
    -0.67
    Lähteet
    -0.67
     lenker
    -0.66
    ]};
    -0.65
    "];
    -0.63
    POSITIVE LOGITS
    -
    0.71
     or
    0.66
     pattern
    0.65
     trend
    0.63
     winner
    0.61
     idea
    0.61
    WHM
    0.56
     answer
    0.56
     shape
    0.56
    cut
    0.56
    Activations Density 0.008%

    No Known Activations