© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16787
    Prev
    Next
    INDEX
    Explanations

    code-related terms associated with programming functions and methods

    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
    RuleContext
    -0.59
    __":
    -0.59
    WebServlet
    -0.58
     оригіналу
    -0.58
    TintMode
    -0.58
    __":
    -0.55
    躇
    -0.52
    ệc
    -0.52
    onOptions
    -0.52
    featureID
    -0.51
    POSITIVE LOGITS
    rungsseite
    0.96
     paramInt
    0.58
    JSONException
    0.57
     يتيمه
    0.54
    равда
    0.49
    RegressionTest
    0.48
     Drapeau
    0.47
    #
    0.47
    ChromeDriver
    0.47
    cheron
    0.47
    Activations Density 0.011%

    No Known Activations