© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1220
    Prev
    Next
    INDEX
    Explanations

    the word "is" in the text

    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.22.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.22.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
     reminiscent
    -0.52
     thiệu
    -0.50
    さっそく
    -0.49
    早速
    -0.48
     possibly
    -0.48
     further
    -0.47
     recently
    -0.47
     reminis
    -0.47
    ticularly
    -0.47
     apparent
    -0.47
    POSITIVE LOGITS
     inherently
    1.08
    تقاوى
    0.93
     intrinsically
    0.85
     EconPapers
    0.84
    inher
    0.84
     ALWAYS
    0.82
     AssemblyCulture
    0.81
    allible
    0.75
     finite
    0.74
     AssemblyProduct
    0.74
    Activations Density 2.303%

    No Known Activations