© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 176
    Prev
    Next
    INDEX
    Explanations

    instances of formatting and punctuation within the text that may indicate different structural components like headers, lists, or code snippets.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    contentLoaded
    -0.83
    AtIndexPath
    -0.64
    StackNavigator
    -0.63
    存于互联网档案馆
    -0.62
     onBackPressed
    -0.61
    expandindo
    -0.59
    Atsauces
    -0.58
     Consequently
    -0.58
    ArrowToggle
    -0.58
    OwnProperty
    -0.57
    POSITIVE LOGITS
     you
    1.44
     make
    1.43
     try
    1.40
     check
    1.33
     remember
    1.23
     Make
    1.21
     take
    1.20
     don
    1.19
     use
    1.18
     ensure
    1.16
    Activations Density 2.238%

    No Known Activations