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. 9127
    Prev
    Next
    INDEX
    Explanations

    references to scientific reviews or journal articles

    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
    AndEndTag
    -0.81
     ब्रेकडाउन
    -0.66
     ویکی‌پدیا
    -0.62
     >=",
    -0.60
    ंदीखरीदारी
    -0.60
     ویکی‌پدیای
    -0.54
     Nons
    -0.53
     pinulongan
    -0.52
     esboço
    -0.52
     kasarigan
    -0.52
    POSITIVE LOGITS
    hasMoreElements
    0.63
    forName
    0.56
    NgModule
    0.55
    redos
    0.52
     ujednoznacz
    0.52
    BeginInit
    0.52
    isOk
    0.52
    EndContext
    0.51
     Horse
    0.50
    antique
    0.50
    Activations Density 0.009%

    No Known Activations