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. 16628
    Prev
    Next
    INDEX
    Explanations

    text related to historical research

    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
     itſelf
    -0.82
     Jefus
    -0.77
     Efq
    -0.72
     myſelf
    -0.72
     fuff
    -0.71
    شهاد
    -0.70
     препратки
    -0.69
     Pauli
    -0.68
     pleaſure
    -0.67
     Beſ
    -0.66
    POSITIVE LOGITS
     historians
    0.55
     Geschichts
    0.53
     Humanities
    0.49
     re
    0.49
     touristes
    0.48
     agences
    0.47
     historian
    0.45
    ]]=
    0.45
     chercheurs
    0.44
     történ
    0.43
    Activations Density 0.040%

    No Known Activations