© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26110
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions involving addition and subtraction

    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
     صوتيه
    -1.11
    Personendaten
    -1.05
    Jeografia
    -0.97
    enderror
    -0.95
     للاسماء
    -0.90
     BoxDecoration
    -0.87
    MLLoader
    -0.81
    Tembelea
    -0.81
     AssemblyCompany
    -0.80
     ddelweddau
    -0.80
    POSITIVE LOGITS
     खरीदा
    0.61
     stand
    0.52
     boys
    0.48
     الداخ
    0.47
    pushFollow
    0.47
    TRX
    0.45
     Med
    0.45
     Stand
    0.45
     推荐
    0.44
    thaus
    0.43
    Activations Density 0.050%

    No Known Activations