© 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. 19508
    Prev
    Next
    INDEX
    Explanations

    references to pilot studies or experiments

    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
     memp
    -0.71
     Hung
    -0.71
    popper
    -0.71
     ràng
    -0.67
     ang
    -0.66
     ph
    -0.63
    angue
    -0.63
     cor
    -0.60
    erna
    -0.59
     paz
    -0.59
    POSITIVE LOGITS
     PILOT
    1.70
     Pilot
    1.66
    Pilot
    1.62
    pilot
    1.59
     Pilots
    1.51
     pilots
    1.49
     pilot
    1.48
     pilo
    1.41
     pilota
    1.29
     Pilate
    1.10
    Activations Density 0.004%

    No Known Activations