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. 31027
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and variables related to equations and relationships in a structured format

    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
    ImageContext
    -0.79
    posedge
    -0.64
    ksikon
    -0.55
     Roskov
    -0.52
    Hochspringen
    -0.52
    erialization
    -0.51
    )_/¯
    -0.50
    uxxxx
    -0.49
    imarães
    -0.49
     Ansel
    -0.48
    POSITIVE LOGITS
    AndroidJUnit
    0.66
    libft
    0.60
    tagHelper
    0.59
    큼
    0.58
     kanssa
    0.54
    RectangleBorder
    0.54
     cref
    0.54
    annica
    0.51
     ComVisible
    0.50
    fortawesome
    0.48
    Activations Density 0.059%

    No Known Activations