© 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. 2-RES-MATRYOSHKA-DC
    7. 3505
    Prev
    Next
    INDEX
    Explanations

    instances of the word "up"

    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
     nav
    -0.52
     final
    -0.49
     Plan
    -0.48
     ste
    -0.48
     diz
    -0.48
    Inggris
    -0.48
     plan
    -0.47
     mengel
    -0.47
     cho
    -0.47
     escolh
    -0.45
    POSITIVE LOGITS
     Pickup
    1.35
     pickup
    1.33
    pickup
    1.30
    Pickup
    1.27
     pickups
    1.13
    #+#
    1.09
    enumi
    1.06
     NgModule
    0.93
    AddHtmlAttribute
    0.89
     snippetHide
    0.87
    Activations Density 0.010%

    No Known Activations