Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 9-RES-MATRYOSHKA-DC
    4. 16688
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "listen".

    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
    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
    aarrggbb
    -0.78
    udesta
    -0.75
     craindre
    -0.75
     Sprague
    -0.73
     piú
    -0.73
     cref
    -0.71
    Референце
    -0.70
    ContentAlignment
    -0.69
     quelcon
    -0.68
     nuages
    -0.67
    POSITIVE LOGITS
     listen
    1.09
     listening
    1.06
     listened
    1.01
     Listening
    1.00
     listens
    0.98
     Listen
    0.94
     LISTEN
    0.91
     listeners
    0.89
    Listen
    0.86
    Listening
    0.85
    Activations Density 0.006%

    No Known Activations