© 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. 16714
    Prev
    Next
    INDEX
    Explanations

    phrases that involve awareness of past events or evidence of prior occurrences

    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
     jsPsych
    -0.51
    UserScript
    -0.50
    ipedi
    -0.49
    clu
    -0.49
    بوابة
    -0.48
    賀状
    -0.47
    ZIONE
    -0.46
    :][
    -0.43
     Kerk
    -0.43
    kill
    -0.42
    POSITIVE LOGITS
    SharedDtor
    0.73
     resourceCulture
    0.61
    rungsseite
    0.60
     تضيفلها
    0.60
    principalTable
    0.59
     مشين
    0.58
    MockMvc
    0.57
    Према
    0.57
    DockStyle
    0.57
     '\\;'
    0.56
    Activations Density 0.318%

    No Known Activations