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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91339
    Prev
    Next
    INDEX
    Explanations

    own

    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
     Down
    -1.05
     downs
    -1.02
    own
    -0.97
     Downs
    -0.96
    Down
    -0.90
    downs
    -0.90
     down
    -0.84
    down
    -0.79
    Downs
    -0.79
     DOWN
    -0.73
    POSITIVE LOGITS
    Datuak
    0.62
    }))
    
    0.54
    }));
    
    0.45
    ligently
    0.43
    tômes
    0.42
    restle
    0.42
     stretch
    0.42
    quelize
    0.42
     kleiner
    0.41
    })]
    0.41
    Activations Density 1.262%

    No Known Activations