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. 32029
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific observations and artifacts, particularly in biological or historical 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
     AssemblyProduct
    -0.75
     OFDb
    -0.65
    XmlAccessType
    -0.64
     nahilalakip
    -0.60
    StreetMap
    -0.60
     '\\;'
    -0.59
    NewUrlParser
    -0.58
    UnsafeEnabled
    -0.58
    roek
    -0.58
     дописавши
    -0.57
    POSITIVE LOGITS
    ThemeOverlay
    0.59
     after
    0.50
    ódz
    0.50
     [](
    0.49
    modb
    0.48
     posteriores
    0.46
     geworden
    0.45
     efter
    0.44
    ($__
    0.43
     Efter
    0.43
    Activations Density 0.207%

    No Known Activations