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. 19043
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and their evaluations

    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
    ftagPool
    -0.72
    Външни
    -0.61
    resave
    -0.61
    Бележки
    -0.59
    uterte
    -0.57
    ByDefault
    -0.56
    eraard
    -0.55
    tagext
    -0.54
     onOptions
    -0.54
    HandlerContext
    -0.52
    POSITIVE LOGITS
     Provision
    0.66
    ']}
    0.63
    atriz
    0.63
    mallows
    0.62
    Provision
    0.62
    lillah
    0.60
     provisional
    0.59
    igure
    0.58
    halter
    0.58
     Provisions
    0.58
    Activations Density 0.002%

    No Known Activations