© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16158
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or variables in a context of equations

    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
     setLoading
    -0.73
    ly
    -0.68
    DateField
    -0.67
    Xna
    -0.65
     Normdatei
    -0.65
    apunov
    -0.64
    lessly
    -0.62
    UVWXYZ
    -0.62
     ParseException
    -0.61
    disks
    -0.61
    POSITIVE LOGITS
    sizeCache
    0.85
    Portail
    0.84
     SDI
    0.80
    WireFormat
    0.79
     l
    0.77
    %)$
    0.76
    </u>
    0.75
    httphttps
    0.75
    ”?
    0.74
    Butyl
    0.74
    Activations Density 0.071%

    No Known Activations