© 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. 115
    Prev
    Next
    INDEX
    Explanations

    strings of words and symbols used in scientific research, math, and medicine

    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
     Conne
    -0.54
    Conne
    -0.53
    <bos>
    -0.51
     trusty
    -0.49
     placés
    -0.49
     Manually
    -0.49
    conven
    -0.48
     appartiennent
    -0.48
     placée
    -0.48
     diberi
    -0.47
    POSITIVE LOGITS
     decrease
    1.14
     increase
    1.10
     significantly
    1.07
     increased
    1.07
     increases
    1.02
     decreased
    1.01
     decreases
    1.00
     dramatically
    0.94
     markedly
    0.94
     caused
    0.87
    Activations Density 15.769%

    No Known Activations