© 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. 5832
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific structural element within forest plots, specifically the stand

    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
     sitting
    -1.93
     Sitting
    -1.68
    sitting
    -1.66
    Sitting
    -1.66
     seated
    -1.48
     sit
    -1.33
     seat
    -1.31
     sentarse
    -1.22
     sat
    -1.14
     sits
    -1.14
    POSITIVE LOGITS
     stand
    2.69
     Stand
    2.44
    Stand
    2.22
    stand
    2.16
     stands
    2.13
     Stands
    2.08
    STAND
    1.97
    stands
    1.93
     STAND
    1.77
     stood
    1.40
    Activations Density 0.016%

    No Known Activations