© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16342
    Prev
    Next
    INDEX
    Explanations

    the word "whether" in various forms

    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
     either
    -0.75
     Either
    -0.69
    Either
    -0.65
     conced
    -0.62
    gi
    -0.61
    either
    -0.60
     odc
    -0.60
    ic
    -0.58
     flip
    -0.57
     Eisenberg
    -0.57
    POSITIVE LOGITS
     GenerationType
    0.96
     ddelweddau
    0.87
     للمعارف
    0.85
    GenerationType
    0.80
     whe
    0.79
    ]")]
    0.79
    gameserver
    0.79
     ComVisible
    0.78
    Handlung
    0.78
    autogui
    0.77
    Activations Density 0.007%

    No Known Activations