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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26081
    Prev
    Next
    INDEX
    Explanations

    expressions and variations of the word "celebrate"

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Imo
    -0.63
    Goo
    -0.63
    })()
    -0.62
    ])));
    -0.62
     Goo
    -0.60
    lini
    -0.60
     )}
    -0.59
    genas
    -0.59
     Imran
    -0.59
    ContentAsync
    -0.58
    POSITIVE LOGITS
     Celebrate
    0.98
    Celebrate
    0.95
     Celebrations
    0.94
     Celebr
    0.91
    celebrate
    0.90
     celebr
    0.89
    Portail
    0.86
    endpush
    0.85
     Kela
    0.83
     CELEBR
    0.83
    Activations Density 0.007%

    No Known Activations