© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 405
    Prev
    Next
    INDEX
    Explanations

    labels and captions in scientific papers that refer to figures and their components

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    mybatisplus
    -1.05
     GenerationType
    -0.82
     EconPapers
    -0.79
     متعلقه
    -0.77
    AndEndTag
    -0.77
    +#+
    -0.76
    SaveChangesAsync
    -0.76
    UIControlState
    -0.74
     AssemblyTitle
    -0.72
     JpaRepository
    -0.72
    POSITIVE LOGITS
     blue
    1.02
     shown
    1.02
     dashed
    1.00
     dotted
    0.97
     arrows
    0.96
     Shown
    0.94
     red
    0.91
     yellow
    0.90
    blue
    0.90
     highlighted
    0.89
    Activations Density 2.754%

    No Known Activations