© 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. 46
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to technology, computer science, or scientific advancement.

    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
     anún
    -0.99
     démocr
    -0.95
     prochaines
    -0.94
     cérami
    -0.91
     attentes
    -0.89
     ouvertes
    -0.85
     vœux
    -0.84
     inconvénients
    -0.84
     fidèles
    -0.84
     preuves
    -0.84
    POSITIVE LOGITS
     various
    1.46
     different
    1.45
     non
    1.40
     individual
    1.40
     large
    1.38
     many
    1.33
     multiple
    1.33
     other
    1.33
     diverse
    1.32
     high
    1.31
    Activations Density 22.241%

    No Known Activations