© 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. 0-CLT-HP
    4. 45073
    Prev
    Next
    INDEX
    Explanations

    currently

    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
    '},
    
    -0.76
    ValueStyle
    -0.73
    '}>
    -0.72
     تضيفلها
    -0.68
    parsedMessage
    -0.67
    '}}>
    -0.63
    ")));
    
    -0.63
    ]),
    
    -0.62
     HasFactory
    -0.62
    ]));
    
    -0.62
    POSITIVE LOGITS
    QPalette
    0.50
     store
    0.47
    انتهای
    0.46
    SOUNDBITE
    0.45
    ViewFeatures
    0.44
     wohnen
    0.44
     QtCore
    0.42
    nowe
    0.42
     use
    0.42
     Suche
    0.42
    Activations Density 0.068%

    No Known Activations