© 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. 3185
    Prev
    Next
    INDEX
    Explanations

    repeated phrases involving the word "well."

    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
    ^(@)
    -0.86
     Jefus
    -0.81
     whoſe
    -0.79
     Schmel
    -0.78
    hogany
    -0.77
     onItemClick
    -0.77
    ✨:
    -0.75
    SBATCH
    -0.75
    toral
    -0.73
     iſt
    -0.72
    POSITIVE LOGITS
     Well
    1.22
    Well
    1.16
     WELL
    1.15
     Welles
    1.09
     well
    1.09
    well
    1.08
     Wells
    1.06
    Wells
    0.97
     wells
    0.97
    Bien
    0.93
    Activations Density 0.100%

    No Known Activations