© 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. 0-RES-MATRYOSHKA-DC
    7. 15208
    Prev
    Next
    INDEX
    Explanations

    the presence of clickable elements associated with user interaction actions

    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
    erunner
    -0.53
    ménage
    -0.52
    cetamol
    -0.52
    ymus
    -0.49
    bear
    -0.49
    뀐
    -0.48
    ourable
    -0.47
     bear
    -0.46
     sambung
    -0.46
     lettres
    -0.46
    POSITIVE LOGITS
     onClick
    3.11
    onClick
    2.41
     onclick
    2.41
    onclick
    2.02
     onChange
    1.50
    OnClick
    1.47
     onPress
    1.43
    onChange
    1.30
    OnClickListener
    1.09
    onPress
    1.08
    Activations Density 0.000%

    No Known Activations