© 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. 900
    Prev
    Next
    INDEX
    Explanations

    the phrase "there are" followed by words indicating quantity or difference

    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
     every
    -0.67
     verksamhet
    -0.66
     this
    -0.63
     a
    -0.60
     one
    -0.60
     Everything
    -0.59
     Every
    -0.58
     aktivitet
    -0.57
     everything
    -0.57
     an
    -0.57
    POSITIVE LOGITS
     ligiloj
    1.01
     kasarigan
    0.95
     indications
    0.90
    TagMode
    0.90
    رشف
    0.86
     Fewer
    0.84
     Efq
    0.83
    ImageContext
    0.81
    AddTagHelper
    0.81
    ंदीखरीदारी
    0.80
    Activations Density 0.325%

    No Known Activations