Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 23185
    Prev
    Next
    INDEX
    Explanations

    references to control commands or functions in programming 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
     Dodson
    -0.71
    AM
    -0.66
    sourceMap
    -0.62
    savefig
    -0.61
    >(&
    -0.60
     Poe
    -0.60
     uParam
    -0.59
     vacun
    -0.59
    γέν
    -0.59
     numberWith
    -0.58
    POSITIVE LOGITS
     ctrl
    1.06
    CTRL
    1.05
     CTRL
    1.02
     Ctrl
    1.02
    gridx
    1.02
    ########.
    0.96
    Ctrl
    0.88
    ähig
    0.85
    躇
    0.84
    tagHelperRunner
    0.83
    Activations Density 0.004%

    No Known Activations