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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 19038
    Prev
    Next
    INDEX
    Explanations

    technical terms related to systems and protocols

    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
     AssemblyCompany
    -0.84
    Datuak
    -0.80
    ViewImports
    -0.69
    曖昧さ回避
    -0.68
     <>",
    -0.66
     <=",
    -0.65
     disambiguazione
    -0.65
    críbete
    -0.64
    +#+#
    -0.64
     calendriers
    -0.62
    POSITIVE LOGITS
    bufio
    0.46
    jupiter
    0.44
    atasaray
    0.44
    人民共和国
    0.43
     Argentino
    0.41
    FAO
    0.40
    migrationBuilder
    0.39
     Peshawar
    0.39
     giri
    0.38
    ùm
    0.38
    Activations Density 1.110%

    No Known Activations