© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 3031
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to voice assistants

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     Paglinawan
    -0.73
     Walkover
    -0.58
    цездатний
    -0.55
     niacin
    -0.54
    +#+#
    -0.54
    ConstraintMaker
    -0.52
     equinox
    -0.52
    mètre
    -0.50
     masak
    -0.50
     countrymen
    -0.50
    POSITIVE LOGITS
     voice
    1.20
     speech
    0.94
     Voice
    0.94
    voice
    0.92
    Voice
    0.88
     conversation
    0.87
     Speech
    0.85
     conversational
    0.84
     voices
    0.83
     recognition
    0.80
    Activations Density 0.120%

    No Known Activations