© 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. 105
    Prev
    Next
    INDEX
    Explanations

    articles "the" and "a" followed by subsequent tokens whose activation values decrease

    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
     graisse
    -0.68
     wikipagina
    -0.68
     ciascuno
    -0.66
     anún
    -0.65
     jambe
    -0.63
     normaux
    -0.63
     figliu
    -0.63
     ognuno
    -0.60
     pérd
    -0.60
     alimentazione
    -0.60
    POSITIVE LOGITS
     same
    1.70
     entire
    1.59
     latter
    1.47
     vast
    1.46
     whole
    1.44
     most
    1.41
     rest
    1.37
     second
    1.37
     final
    1.36
     usual
    1.36
    Activations Density 6.520%

    No Known Activations