© 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. 321
    Prev
    Next
    INDEX
    Explanations

    terms related to programming structures and directives in C++ code

    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
    DeleteBehavior
    -0.94
    MessageTagHelper
    -0.90
    elemField
    -0.88
    URLException
    -0.82
    ChildScrollView
    -0.82
    IVEREF
    -0.82
     SwitchCompat
    -0.82
    Geplaatst
    -0.81
    IsContent
    -0.80
    PreferredItem
    -0.80
    POSITIVE LOGITS
    SessionManager
    0.54
    nesc
    0.51
    έσ
    0.50
    Dougall
    0.49
     Nia
    0.49
     Италијани
    0.49
    ToDisplay
    0.48
    製
    0.47
     reafon
    0.47
     jsPsych
    0.47
    Activations Density 1.730%

    No Known Activations