© 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. 8817
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the beginning or end of events or experiences

    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
     réguli
    -0.65
     trwa
    -0.61
     fabbrica
    -0.60
     regolare
    -0.60
     setData
    -0.59
     terbatas
    -0.59
    างเกง
    -0.59
     cheminée
    -0.58
    ՝
    -0.58
    Véase
    -0.56
    POSITIVE LOGITS
    ']")
    0.85
    ReusableCell
    0.84
    олові
    0.83
    ագրություններ
    0.82
    atrième
    0.78
    PerformLayout
    0.77
    StoryboardSegue
    0.77
    ."],
    0.76
     فريبيس
    0.75
     للاسماء
    0.75
    Activations Density 0.019%

    No Known Activations