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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14176
    Prev
    Next
    INDEX
    Explanations

    the word "alongside" and some words nearby it.

    oai_token-act-pair · gemini-2.0-flash

    alongside

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.76
    preserved
    -0.74
     alongside
    -0.73
    ">//
    -0.73
     onCreateView
    -0.66
    IFUL
    -0.66
    
    -0.65
     المعيارى
    -0.65
    expandindo
    -0.65
     preserve
    -0.65
    POSITIVE LOGITS
    }))
    
    0.65
    UrlResolution
    0.55
    }));
    
    0.53
     })
    
    0.53
    HasForeignKey
    0.49
     CVT
    0.49
     DSG
    0.48
     '\\;'
    0.47
    ConverterFactory
    0.47
     }))
    0.46
    Activations Density 0.821%

    No Known Activations