© 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. 6899
    Prev
    Next
    INDEX
    Explanations

    sentences or statements about talking, discussing, or engaging in conversation

    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
    DISCUSSION
    -0.86
    Discussion
    -0.82
     DISCUSSION
    -0.79
     discussão
    -0.77
     discusión
    -0.76
    enderror
    -0.74
    discussion
    -0.74
     Discussion
    -0.72
     Thread
    -0.68
    discussions
    -0.66
    POSITIVE LOGITS
     talk
    2.80
    talk
    2.63
     Talk
    2.53
    Talk
    2.48
     TALK
    2.36
     talking
    2.19
    TALK
    2.11
     talked
    2.00
    talking
    1.99
     talks
    1.98
    Activations Density 0.016%

    No Known Activations