© 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. 18-RES-MATRYOSHKA-DC
    7. 176
    Prev
    Next
    INDEX
    Explanations

    transitions and discourse markers, such as logical connections, lists, and examples

    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.18.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.18.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
    volles
    -0.57
    jącego
    -0.52
    ertes
    -0.49
    __*/
    -0.49
    enance
    -0.48
    libft
    -0.48
     resourceCulture
    -0.47
    jącej
    -0.47
     %@",
    -0.47
     gì
    -0.46
    POSITIVE LOGITS
     these
    2.69
     These
    2.36
    these
    2.34
    These
    2.28
     THESE
    2.03
    これらの
    1.98
    這些
    1.94
    这些
    1.94
     those
    1.76
    它们
    1.75
    Activations Density 4.931%

    No Known Activations