© 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. 324
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to measurement outcomes in studies

    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
    плек
    -0.83
    مصادر
    -0.82
    ISupport
    -0.65
    Muri
    -0.65
     Billings
    -0.62
    bestimm
    -0.61
    мум
    -0.61
    Välislingid
    -0.61
    zucker
    -0.60
     muri
    -0.59
    POSITIVE LOGITS
    subsection
    1.02
    subsubsection
    0.70
    PyExc
    0.69
    اریخ
    0.66
    httphttps
    0.65
    databind
    0.64
     Mö
    0.63
     /\.
    0.63
    FTE
    0.62
    ViewFeatures
    0.62
    Activations Density 1.478%

    No Known Activations