© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 28833
    Prev
    Next
    INDEX
    Explanations

    the word "of" in various contexts, indicating its significant and repetitive presence in the text

    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
    Negative Logits
     ]
    -0.61
    ".
    -0.58
     “.
    -0.55
    moduleId
    -0.54
    )".
    -0.52
    ]").
    -0.52
     }}"></
    -0.52
     ")
    -0.51
    ]').
    -0.51
    mtliche
    -0.49
    POSITIVE LOGITS
    IsContent
    0.83
    IntoConstraints
    0.67
     hâte
    0.66
    χρι
    0.65
     Réponses
    0.65
    Executives
    0.64
    XMLSchema
    0.64
    StoreMessageInfo
    0.64
     wireType
    0.63
     cohomology
    0.63
    Activations Density 0.002%

    No Known Activations