© 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
    2. Gemma-2-2B
    3. 18-RES-MATRYOSHKA-DC
    4. 54
    Prev
    Next
    INDEX
    Explanations

    parenthetical and bracketing expressions referencing figures and lemmas from research articles

    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
    '));
    
    -0.68
    {}".
    -0.57
    {}",
    -0.56
    "]);
    
    -0.56
     et
    -0.56
    ]);
    
    -0.55
    ...]
    -0.55
     en
    -0.55
     disponibilités
    -0.54
     las
    -0.52
    POSITIVE LOGITS
    aka
    0.98
    see
    0.94
    including
    0.89
    or
    0.88
    which
    0.86
     Phry
    0.84
    !!!)
    0.83
     Jock
    0.82
     Christendom
    0.82
    OGND
    0.81
    Activations Density 2.157%

    No Known Activations