© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 925
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to electronics and their features

    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
     Efq
    -1.09
    RenderAtEndOf
    -1.02
    ſelves
    -1.01
     myſelf
    -0.97
     betweenstory
    -0.96
    StreetMap
    -0.95
    ſelf
    -0.88
    ^(@)
    -0.87
     EconPapers
    -0.85
     auffi
    -0.85
    POSITIVE LOGITS
     
    0.88
     designed
    0.65
     boasts
    0.64
     premium
    0.63
     features
    0.63
    Designed
    0.63
    <eos>
    0.62
     dual
    0.62
     Designed
    0.62
     design
    0.62
    Activations Density 1.459%

    No Known Activations