© 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. 4821
    Prev
    Next
    INDEX
    Explanations

    references to visual focus or expressions indicating emotion

    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
    seye
    -0.60
     Eye
    -0.59
    toHaveBeenCalled
    -0.56
     personal
    -0.55
    Eye
    -0.53
    +"\
    -0.53
    side
    -0.52
     eye
    -0.52
    ))->
    -0.52
     EYE
    -0.51
    POSITIVE LOGITS
     hands
    0.93
     palms
    0.81
     arms
    0.80
     fingers
    0.80
    AddTagHelper
    0.79
     StringTokenizer
    0.71
     HANDS
    0.69
    Hands
    0.69
    hashtags
    0.67
     eyes
    0.66
    Activations Density 0.358%

    No Known Activations