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. 2-RES-MATRYOSHKA-DC
    4. 47
    Prev
    Next
    INDEX
    Explanations

    references to legal disclaimers, licensing, and liability clauses

    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
     ftate
    -0.86
     poffible
    -0.86
     fubject
    -0.82
     caufe
    -0.79
     purpoſe
    -0.77
     reafon
    -0.75
     itſelf
    -0.74
     autoradio
    -0.74
     Aton
    -0.73
     OnInit
    -0.71
    POSITIVE LOGITS
     and
    2.31
     AND
    1.62
     và
    1.61
     And
    1.55
    and
    1.51
     \&
    1.48
    และ
    1.46
     и
    1.38
     그리고
    1.37
     και
    1.36
    Activations Density 9.132%

    No Known Activations