© 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. 2903
    Prev
    Next
    INDEX
    Explanations

    sequences that describe sequential actions or steps in a procedure

    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
     cauza
    -0.68
    slidesPer
    -0.66
    kkue
    -0.63
     Dostupné
    -0.62
    mær
    -0.58
     âgées
    -0.56
    phalt
    -0.56
     pauvres
    -0.55
    classnames
    -0.55
     redan
    -0.54
    POSITIVE LOGITS
     followed
    1.05
     Followed
    1.03
    followed
    0.95
    Followed
    0.90
     Danach
    0.88
     diikuti
    0.79
     danach
    0.77
     Daarna
    0.74
     Thereafter
    0.71
     thereafter
    0.68
    Activations Density 0.042%

    No Known Activations