© 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. 6725
    Prev
    Next
    INDEX
    Explanations

    text containing specific characters and sequences from certain non-Latin scripts

    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
    __*/
    -0.61
     )}$
    -0.59
     насељу
    -0.58
    Portály
    -0.57
     kor
    -0.55
    Personendaten
    -0.55
    existsSync
    -0.54
    ască
    -0.52
     跳转至
    -0.52
     fel
    -0.51
    POSITIVE LOGITS
     loren
    0.76
     Athenians
    0.66
    Personensuche
    0.65
     Shakspeare
    0.64
     Cæsar
    0.63
    formin
    0.63
     fowls
    0.60
     saira
    0.59
     fourrure
    0.58
     staffel
    0.58
    Activations Density 0.350%

    No Known Activations