© 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. 20860
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to imaginary and real components in complex functions or frequencies

    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
    IntoConstraints
    -0.75
    Enllaços
    -0.74
    opsida
    -0.71
    metz
    -0.63
    buttonShape
    -0.62
    enfance
    -0.58
     роза
    -0.57
    Хьажоргаш
    -0.56
     SqlCommand
    -0.56
    COUVER
    -0.56
    POSITIVE LOGITS
     ་་
    0.53
     AssemblyVersion
    0.52
    原始内容存档于
    0.48
     Saigon
    0.48
     ſmall
    0.47
     Diſ
    0.46
     Confucian
    0.46
     iveco
    0.46
     uſ
    0.45
     himſelf
    0.45
    Activations Density 0.003%

    No Known Activations