© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 5495
    Prev
    Next
    INDEX
    Explanations

    references to segments in various contexts

    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
     onlyOwner
    -0.88
     Makefile
    -0.83
     cómics
    -0.79
     byen
    -0.79
    idopsis
    -0.78
     Michoacán
    -0.77
     Falco
    -0.76
     Trus
    -0.75
     Puk
    -0.75
    mstyle
    -0.73
    POSITIVE LOGITS
     Segment
    1.41
     segment
    1.40
     segments
    1.38
    Segment
    1.36
     Segments
    1.28
    segments
    1.22
    Segments
    1.21
    segment
    1.18
     SEG
    1.12
    SEGMENT
    1.10
    Activations Density 0.041%

    No Known Activations