© 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. 458
    Prev
    Next
    INDEX
    Explanations

    code snippets, mathematical expressions, or structured data with specific patterns

    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
    IntoConstraints
    -0.64
     nakalista
    -0.63
    ="@+
    -0.55
    ➍
    -0.52
     quadruple
    -0.50
    IVEREF
    -0.49
    ConstraintMaker
    -0.48
     fourteenth
    -0.48
    ulic
    -0.47
     Thirteen
    -0.47
    POSITIVE LOGITS
    2
    1.48
    ２
    1.13
     two
    1.05
    ২
    1.01
     deuxième
    0.99
     deux
    0.97
     Two
    0.96
     ২
    0.95
    २
    0.94
     ۲
    0.94
    Activations Density 4.124%

    No Known Activations