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. 15471
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and terms related to physical quantities in scientific contexts

    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
     <<<<<<<<<<<<<<
    -0.79
     EconPapers
    -0.77
    KommentareTeilen
    -0.72
    Tembelea
    -0.67
    principalTable
    -0.65
     للمعارف
    -0.64
    zono
    -0.64
    ftagPool
    -0.64
    esModule
    -0.63
    bewerken
    -0.63
    POSITIVE LOGITS
     CommonModule
    0.52
     тетра
    0.45
    secondary
    0.43
     setTotal
    0.41
    левой
    0.40
     sidor
    0.40
    添
    0.40
     menyem
    0.39
    astanza
    0.39
     vieille
    0.39
    Activations Density 0.016%

    No Known Activations