© 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. 2120
    Prev
    Next
    INDEX
    Explanations

    out

    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
    )];
    
    -0.74
    ])));
    -0.72
    ]").
    -0.72
    '))
    
    -0.70
    ]').
    -0.69
    ]));
    
    -0.68
    '));
    
    -0.67
    ])):
    -0.66
    :].
    -0.65
    ]");
    -0.65
    POSITIVE LOGITS
    ,
    0.78
    tagHelperRunner
    0.64
    Personensuche
    0.57
     définiti
    0.56
    
    0.54
    Hochspringen
    0.54
    LookAnd
    0.54
    Související
    0.50
    rawDesc
    0.49
     faibles
    0.48
    Activations Density 0.000%

    No Known Activations