© 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. 4202
    Prev
    Next
    INDEX
    Explanations

    references to conceptual or mathematical interest

    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
     étoit
    -0.67
     beſt
    -0.65
    odd
    -0.63
     odd
    -0.62
     surprise
    -0.62
     Borel
    -0.62
     morire
    -0.62
     noires
    -0.61
    wezig
    -0.60
     atypical
    -0.60
    POSITIVE LOGITS
     interesting
    2.36
    interesting
    2.20
     Interesting
    2.03
    Interesting
    1.94
     interessante
    1.67
     interesante
    1.67
     intéressante
    1.63
     intéressant
    1.44
     interessanti
    1.43
     interesantes
    1.41
    Activations Density 0.014%

    No Known Activations