© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3263
    Prev
    Next
    INDEX
    Explanations

    the word "be" within mathematical problems

    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
    Negative Logits
     intptr
    -0.65
    Поздрав
    -0.63
    ifflin
    -0.62
     "..\..\
    -0.61
    dicional
    -0.59
    isticated
    -0.59
     Chambres
    -0.59
     Declare
    -0.58
    ícil
    -0.57
    })));
    -0.57
    POSITIVE LOGITS
     be
    0.89
     Be
    0.63
    Be
    0.62
    IntoConstraints
    0.56
     onPause
    0.56
     PyObject
    0.49
    ConstraintMaker
    0.49
    be
    0.49
     aient
    0.49
    <tbody>
    0.48
    Activations Density 0.022%

    No Known Activations