© 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. 741
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or terms related to square roots and operations involving them

    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
    ГЛА
    -0.59
     ple
    -0.57
     تد
    -0.57
    adaptiveStyles
    -0.57
     Howe
    -0.56
    inquirer
    -0.56
    ageo
    -0.56
     Ser
    -0.55
    +#+#
    -0.55
    eve
    -0.54
    POSITIVE LOGITS
    sqrt
    1.75
    qrt
    1.63
     sqrt
    1.53
    Sqrt
    1.15
    √
    1.05
     √
    1.02
    ∛
    0.87
    
    0.75
     căn
    0.74
    PathParam
    0.72
    Activations Density 0.216%

    No Known Activations