© 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. 175
    Prev
    Next
    INDEX
    Explanations

    abbreviations, acronyms, and equations in scientific or technical texts

    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
     raiſ
    -1.00
     iſt
    -0.95
    ſelf
    -0.94
     ſche
    -0.91
     Theſe
    -0.90
     verſ
    -0.88
     ―――――
    -0.88
     Titi
    -0.87
     ſever
    -0.87
     myſelf
    -0.87
    POSITIVE LOGITS
    G
    0.71
    Viitteet
    0.69
     nationaux
    0.68
    C
    0.68
    [toxicity=0]
    0.68
    B
    0.67
    ษา
    0.66
    Przypisy
    0.66
    E
    0.65
    P
    0.64
    Activations Density 2.404%

    No Known Activations