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. 16544
    Prev
    Next
    INDEX
    Explanations

    the word "respectively"

    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
     houſe
    -0.69
     ſche
    -0.62
     ſel
    -0.60
     pleaſure
    -0.58
     ſte
    -0.57
     ſmall
    -0.57
     fevere
    -0.57
     raiſ
    -0.57
     realized
    -0.56
     ſch
    -0.55
    POSITIVE LOGITS
    aarrggbb
    0.70
     ddelweddau
    0.69
     utafitiHapana
    0.66
    󠁢
    0.61
     OnInit
    0.60
    AutoScaleMode
    0.60
    Hochspringen
    0.60
    MessageOf
    0.59
     فريبيس
    0.59
    исленность
    0.57
    Activations Density 0.008%

    No Known Activations