© 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. 0-RES-MATRYOSHKA-DC
    7. 11915
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific concepts or datasets

    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
     détru
    -0.57
     ziyaretçi
    -0.51
     umane
    -0.50
     immunos
    -0.49
    apest
    -0.49
     Той
    -0.48
     nahilalakip
    -0.48
    manfaat
    -0.48
     ivelany
    -0.48
     []).
    -0.47
    POSITIVE LOGITS
     doi
    1.04
    Griff
    0.79
    clusal
    0.79
     Brotherhood
    0.79
     Griffith
    0.77
    ér
    0.76
     mant
    0.75
     pact
    0.73
    ματα
    0.73
     Sarg
    0.73
    Activations Density 0.031%

    No Known Activations