© 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. 3-RES-MATRYOSHKA-DC
    7. 15
    Prev
    Next
    INDEX
    Explanations

    scientific notation, especially formulas and data about quantities; it seems to prefer text including math symbols or programming-language like code

    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
    UIControlState
    -0.58
     Thier
    -0.57
    StrictEqual
    -0.54
     cuillère
    -0.53
    YourGuide
    -0.53
     Borja
    -0.53
     medesimo
    -0.51
     boste
    -0.51
    チコミ
    -0.51
    CompleteListener
    -0.50
    POSITIVE LOGITS
     N
    1.44
    N
    1.24
     Ns
    1.19
    Ns
    1.13
     n
    1.09
     Nugent
    1.03
     Nook
    1.02
     NU
    1.00
     Nunes
    1.00
     Naf
    1.00
    Activations Density 6.806%

    No Known Activations