© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5668
    Prev
    Next
    INDEX
    Explanations

    parts of words related to the suffix "el"

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.66
     يتيمه
    -0.66
    ArrowToggle
    -0.64
    StoryboardSegue
    -0.64
     nakalista
    -0.63
    featureID
    -0.63
     bezeichneter
    -0.62
    InvalidProtocol
    -0.61
     ListTile
    -0.60
     متعلقه
    -0.60
    POSITIVE LOGITS
    el
    3.81
    EL
    2.66
    els
    2.20
     el
    2.02
    El
    1.80
     EL
    1.70
     El
    1.69
    elni
    1.56
    elk
    1.55
    ela
    1.54
    Activations Density 0.022%

    No Known Activations