© 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. 8897
    Prev
    Next
    INDEX
    Explanations

    references to cumulative data or cumulative effects

    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
    Carter
    -0.73
     waz
    -0.73
     Carter
    -0.70
     tayo
    -0.69
     Tp
    -0.66
    SharedDtor
    -0.66
    XmlAccessType
    -0.66
    MLLoader
    -0.66
     Beller
    -0.66
    saraba
    -0.65
    POSITIVE LOGITS
     CUM
    1.18
    cumulative
    1.16
    CUM
    1.14
    Cumulative
    1.13
     Cumulative
    1.12
     cumulative
    1.09
     cumul
    1.02
     cum
    1.01
     Cum
    0.99
    Cum
    0.97
    Activations Density 0.002%

    No Known Activations