© 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. 22-RES-MATRYOSHKA-DC
    7. 1002
    Prev
    Next
    INDEX
    Explanations

    content related to audio devices and speech synthesis

    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
    Not in Any Lists

    No Comments

    Negative Logits
     fluorescence
    -0.56
     الرياضيه
    -0.54
    magini
    -0.52
     Fluorescence
    -0.51
     scattata
    -0.51
    usehen
    -0.47
    ofluorescence
    -0.47
     Braw
    -0.47
     fotografico
    -0.47
    υμα
    -0.47
    POSITIVE LOGITS
     audio
    1.75
     sound
    1.70
     Audio
    1.59
     Sound
    1.53
     listening
    1.50
    Audio
    1.48
    sound
    1.48
    audio
    1.47
    Sound
    1.46
     hearing
    1.45
    Activations Density 1.146%

    No Known Activations