© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20272
    Prev
    Next
    INDEX
    Explanations

    transitional phrases or conjunctions that connect thoughts or ideas within a 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
     <=",
    -0.59
    Fordítás
    -0.57
    GraphicsUnit
    -0.57
    WriteBarrier
    -0.53
     bulunur
    -0.51
    sw
    -0.48
    UTOR
    -0.48
    denes
    -0.46
     erstmals
    -0.45
    orteur
    -0.44
    POSITIVE LOGITS
    LayoutConstraint
    0.69
     ujednoznacz
    0.69
     Rasul
    0.68
     تانيه
    0.66
     ceram
    0.65
     Euphrates
    0.63
     препратки
    0.62
    Демографія
    0.62
     Catalana
    0.61
     Spinoza
    0.60
    Activations Density 0.022%

    No Known Activations