© 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. 14352
    Prev
    Next
    INDEX
    Explanations

    references to a specific Amazon Echo device

    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
    colgroup
    -0.59
    bootstrapcdn
    -0.59
    typeorm
    -0.57
    hdashline
    -0.54
    ClientSize
    -0.50
    icza
    -0.48
    bila
    -0.48
     combineReducers
    -0.48
    stylers
    -0.48
    makeText
    -0.47
    POSITIVE LOGITS
    ECHO
    2.59
     Echo
    2.42
     ECHO
    2.30
    Echo
    2.05
    ECH
    0.70
     Ech
    0.70
    Ech
    0.68
     Echoes
    0.67
    timewa
    0.63
    othelioma
    0.60
    Activations Density 0.001%

    No Known Activations