© 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. 8667
    Prev
    Next
    INDEX
    Explanations

    references to the Linotype machine and related terminology

    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
     jadx
    -0.94
    +:+
    -0.91
     Warsaw
    -0.89
     TextInputType
    -0.88
     uſe
    -0.88
    kward
    -0.84
    Leeds
    -0.84
     Nantes
    -0.82
    __*/
    -0.82
     Duane
    -0.82
    POSITIVE LOGITS
     Lin
    1.49
    Lin
    1.22
    lin
    1.10
     Lincoln
    1.06
     lin
    0.97
    Lincoln
    0.95
     Linde
    0.90
     LIN
    0.85
     LINCOLN
    0.82
     Ramsay
    0.80
    Activations Density 0.021%

    No Known Activations