© 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. 17441
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and relations in a formal context

    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
     springfox
    -0.55
    躇
    -0.51
     copy
    -0.49
    Copy
    -0.49
    Thrown
    -0.47
     Copy
    -0.47
    copy
    -0.46
    tanleria
    -0.46
     kuj
    -0.46
    wyczaj
    -0.44
    POSITIVE LOGITS
    richTextPanel
    0.67
     églises
    0.65
    >';
    0.60
    FieldOffset
    0.59
     marbre
    0.59
    PostBack
    0.59
     htmlFor
    0.59
    AsUp
    0.58
    balleur
    0.57
    Redaktion
    0.56
    Activations Density 0.023%

    No Known Activations