© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2761
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "fast" or "rapid" processes or characteristics

    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
     immediately
    -1.04
    immediately
    -0.96
    Immediately
    -0.94
     Immediate
    -0.93
    Immediate
    -0.93
     inmediatamente
    -0.92
     promptly
    -0.91
     Immediately
    -0.91
     IMMEDIATE
    -0.89
     immediate
    -0.88
    POSITIVE LOGITS
     Fast
    2.56
    fast
    2.53
    Fast
    2.52
     fast
    2.47
    FAST
    2.02
     FAST
    1.96
     faſt
    1.38
     fasting
    1.19
     Fasting
    1.07
     fastest
    1.04
    Activations Density 0.022%

    No Known Activations