© 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. 20180
    Prev
    Next
    INDEX
    Explanations

    specific mathematical symbols or algebraic expressions

    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
    Datuak
    -0.75
     تضيفلها
    -0.74
    rawDesc
    -0.74
    存于互联网档案馆
    -0.73
    ReusableCell
    -0.70
     flamma
    -0.66
    phans
    -0.66
    ſelf
    -0.65
     Mende
    -0.65
    ГЛА
    -0.65
    POSITIVE LOGITS
     reda
    0.45
    mphony
    0.43
    DialogContent
    0.40
    strptime
    0.40
    tiken
    0.40
    とある
    0.38
    bro
    0.38
     emerg
    0.38
    хьтан
    0.38
    ustra
    0.37
    Activations Density 0.039%

    No Known Activations