© 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. 3-RES-MATRYOSHKA-DC
    7. 1484
    Prev
    Next
    INDEX
    Explanations

    the word "switch" and words associated with change

    oai_token-act-pair · gemini-2.0-flash
    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
    thâu
    -0.66
     صوتيه
    -0.60
     humaines
    -0.59
     שוליים
    -0.57
     собою
    -0.57
     Egan
    -0.54
     chiara
    -0.54
    entown
    -0.53
     doccia
    -0.53
    ModelSerializer
    -0.53
    POSITIVE LOGITS
     switch
    3.42
     Switch
    3.17
     switches
    3.17
    switch
    3.13
    Switch
    3.03
     SWITCH
    2.98
     switching
    2.97
     switched
    2.92
     Switches
    2.89
     Switching
    2.86
    Activations Density 0.128%

    No Known Activations