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. 25124
    Prev
    Next
    INDEX
    Explanations

    phrases related to the issuance of patents or methods

    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
     HasFactory
    -0.58
     ostavi
    -0.52
    unmodifiable
    -0.47
    __[
    -0.46
    :✨
    -0.46
    enschap
    -0.46
    ContextHolder
    -0.45
     delen
    -0.43
    expiresIn
    -0.43
    insee
    -0.42
    POSITIVE LOGITS
    RectangleBorder
    0.59
     Biôgrafia
    0.56
     BnF
    0.54
    arXiv
    0.54
    makedirs
    0.53
    Бахар
    0.52
    ANTLR
    0.51
    yaszt
    0.51
    cjonal
    0.51
     konserv
    0.50
    Activations Density 0.488%

    No Known Activations