© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 2185
    Prev
    Next
    INDEX
    Explanations

    words ending in "et", "lis", "fil", "swit", "sy", or "us."

    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
     getItemId
    -0.49
    twimg
    -0.48
    AddTagHelper
    -0.47
    CloseOperation
    -0.43
     ExecuteAsync
    -0.42
     Sees
    -0.41
    pielen
    -0.40
    viers
    -0.40
    WindowListener
    -0.40
    setcounter
    -0.40
    POSITIVE LOGITS
    che
    0.87
    ches
    0.86
    chs
    0.82
    ch
    0.82
    cha
    0.82
    Ch
    0.81
    chi
    0.80
    chowa
    0.79
    chae
    0.79
     ch
    0.78
    Activations Density 0.332%

    No Known Activations