© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2838
    Prev
    Next
    INDEX
    Explanations

    the word "hear" in various contexts

    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
     sound
    -1.43
    sound
    -1.30
     Sound
    -1.24
    Sound
    -1.18
    SOUND
    -1.06
     SOUND
    -1.02
     sounds
    -0.86
     noise
    -0.83
     voice
    -0.82
    sounds
    -0.79
    POSITIVE LOGITS
     hear
    2.59
     hears
    2.25
     heard
    2.19
     Hear
    2.05
    Hear
    1.95
     HEAR
    1.91
    hear
    1.88
    heard
    1.76
    Heard
    1.64
     Heard
    1.59
    Activations Density 0.015%

    No Known Activations