© 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. 12-RES-MATRYOSHKA-DC
    7. 25655
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical operations involving splits or divisions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     '\\;'
    -0.89
    })}$
    -0.72
    djangoproject
    -0.71
    /></
    -0.71
    reszcie
    -0.70
    aligned
    -0.70
    CodeAnalysis
    -0.67
    TintMode
    -0.67
    >--}}
    -0.67
    bootstrapcdn
    -0.67
    POSITIVE LOGITS
    split
    0.85
    Split
    0.73
    SPLIT
    0.69
     Split
    0.69
     split
    0.64
    splits
    0.61
    คล
    0.61
    Whit
    0.59
    uple
    0.58
     WHIT
    0.56
    Activations Density 0.000%

    No Known Activations