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. 16593
    Prev
    Next
    INDEX
    Explanations

    mentions of the 21st century

    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
     يتيمه
    -0.62
    onAttach
    -0.60
    AsUp
    -0.58
    ngdoc
    -0.57
    expandindo
    -0.56
     validamos
    -0.56
    thenReturn
    -0.54
    󠁣
    -0.54
    tagHelperRunner
    -0.53
    openzeppelin
    -0.53
    POSITIVE LOGITS
    UnitTesting
    0.76
    inari
    0.56
     munc
    0.53
     Soccerway
    0.51
    bison
    0.51
     Gigabit
    0.51
     belongs
    0.50
     Auger
    0.50
     COMPLE
    0.50
     allu
    0.49
    Activations Density 0.009%

    No Known Activations