© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 6313
    Prev
    Next
    INDEX
    Explanations

    questions about identifying prime factors or divisors of numbers

    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
     firſt
    -0.81
     purpoſe
    -0.80
     Efq
    -0.79
     Theſe
    -0.78
     uſe
    -0.77
     ſeveral
    -0.77
     beſt
    -0.76
    يميديا
    -0.75
     leaſt
    -0.75
     greateſt
    -0.75
    POSITIVE LOGITS
     ComVisible
    0.52
     виправивши
    0.50
     CanadaChoose
    0.48
    PyExc
    0.47
    indd
    0.47
    OGND
    0.46
    jstor
    0.46
     deler
    0.45
    ::_('
    0.45
    claren
    0.45
    Activations Density 1.453%

    No Known Activations