© 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. 8587
    Prev
    Next
    INDEX
    Explanations

    references to boundaries and transitions 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
     jadx
    -0.81
    NameInMap
    -0.75
    OGND
    -0.71
    IntoConstraints
    -0.65
    sidemargin
    -0.65
     насељу
    -0.63
    tagHelperRunner
    -0.62
    PhysRevD
    -0.61
    KommentareTeilen
    -0.61
     հղումներ
    -0.59
    POSITIVE LOGITS
     memasuki
    0.54
     transition
    0.54
     ingresso
    0.50
     Transition
    0.50
    transition
    0.49
     مباشرة
    0.49
     transitioned
    0.48
     Into
    0.47
     Übergang
    0.47
     interfaces
    0.47
    Activations Density 0.081%

    No Known Activations