Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14482
    Prev
    Next
    INDEX
    Explanations

    references to institutional departments or organizational units

    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
     ossia
    -0.55
     heißt
    -0.51
     hieß
    -0.50
    wnie
    -0.49
     district
    -0.49
    ERG
    -0.49
     подготовка
    -0.48
     vivant
    -0.48
    agregar
    -0.48
    openqa
    -0.47
    POSITIVE LOGITS
    Dept
    2.55
     Dept
    1.52
    DEPT
    1.52
    dept
    1.26
     DEPT
    1.21
     dept
    1.09
    +#+#
    0.77
    webElementXpaths
    0.70
    المشاركات
    0.66
    MethodManager
    0.66
    Activations Density 0.000%

    No Known Activations