© 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. 23723
    Prev
    Next
    INDEX
    Explanations

    instances of empty strings or placeholders 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
    Not in Any Lists

    No Comments

    Negative Logits
     useAppContext
    -0.77
     Charlemagne
    -0.68
     pleaſure
    -0.68
    клопе
    -0.68
    theless
    -0.63
     entanto
    -0.63
     purpoſe
    -0.62
     againſt
    -0.62
     "..\..\..\
    -0.61
    CFA
    -0.61
    POSITIVE LOGITS
    存于互联网档案馆
    0.63
    Geplaatst
    0.62
    onces
    0.61
    ButtonModule
    0.59
    rencies
    0.58
     Menschen
    0.57
    \{\\
    0.57
    helves
    0.57
    #!/
    0.57
    Menschen
    0.56
    Activations Density 0.001%

    No Known Activations