© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16090
    Prev
    Next
    INDEX
    Explanations

    words related to specifications or defining parameters

    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
     שוליים
    -0.69
     specific
    -0.65
     ویکی‌پدیای
    -0.62
    Specifically
    -0.62
     specifically
    -0.60
    Искәрмәләр
    -0.60
     bVar
    -0.59
     spezif
    -0.59
     autorytatywna
    -0.58
     dataSnapshot
    -0.57
    POSITIVE LOGITS
    pecified
    0.93
     Specify
    0.90
    ValueStyle
    0.86
     Specifies
    0.83
    betic
    0.82
     Azo
    0.81
     Specified
    0.79
    afone
    0.78
     initComponents
    0.78
    urity
    0.77
    Activations Density 0.012%

    No Known Activations