© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15769
    Prev
    Next
    INDEX
    Explanations

    references to sounds or noises

    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
     voice
    -1.30
     noise
    -1.24
     Voice
    -1.18
     Noise
    -1.18
    Noise
    -1.16
    Voice
    -1.09
    voice
    -1.09
    noise
    -1.07
     VOICE
    -0.97
     NOISE
    -0.87
    POSITIVE LOGITS
     sounds
    2.30
     Sounds
    2.05
    sounds
    1.91
    Sounds
    1.88
     klingt
    1.09
     sonidos
    1.02
     terdengar
    0.90
     suena
    0.89
     klink
    0.70
     sounded
    0.62
    Activations Density 0.002%

    No Known Activations