© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1602
    Prev
    Next
    INDEX
    Explanations

    code/errors

    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
     définiti
    -0.74
     ARXIV
    -0.73
     réguli
    -0.72
     déchir
    -0.72
     hâte
    -0.71
     igång
    -0.71
     quelcon
    -0.70
     profondità
    -0.69
     copertura
    -0.69
     kabát
    -0.69
    POSITIVE LOGITS
     })
    
    0.74
    }),
    
    0.73
    })}
    0.72
    })),
    0.72
    ])
    
    0.71
    =_
    0.71
    })
    
    0.71
     _
    0.70
    }}},
    0.70
     дописавши
    0.70
    Activations Density 0.501%

    No Known Activations