© 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. 482
    Prev
    Next
    INDEX
    Explanations

    function oriented stop words and separators

    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
    getreten
    -0.63
     sağlar
    -0.59
     kullanılır
    -0.57
     vermeiden
    -0.55
     содержи
    -0.52
    ^(@)
    -0.52
     gangen
    -0.52
     introducido
    -0.51
     दें
    -0.51
     prévue
    -0.51
    POSITIVE LOGITS
     making
    1.86
     having
    1.73
     being
    1.73
     taking
    1.72
     getting
    1.71
     giving
    1.64
     creating
    1.61
     putting
    1.59
     doing
    1.59
     providing
    1.52
    Activations Density 5.669%

    No Known Activations