© 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. 1885
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terms related to summation and proofs

    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
    developed
    -0.44
    ();*/
    -0.43
     G
    -0.43
    uttavia
    -0.41
    Enllaces
    -0.41
     /
    -0.40
     Fa
    -0.40
    جه
    -0.40
    годня
    -0.40
     Besar
    -0.40
    POSITIVE LOGITS
    новниш
    0.90
     ویکی‌پدی
    0.84
     AssemblyCulture
    0.83
     Мексичка
    0.79
    PerformLayout
    0.77
    GEBURTSDATUM
    0.76
     Facult
    0.74
     Majefty
    0.74
     propOrder
    0.74
     Allegretto
    0.73
    Activations Density 1.296%

    No Known Activations