© 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. 1698
    Prev
    Next
    INDEX
    Explanations

    technical research terms and reagents

    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
    i
    -0.90
    tling
    -0.89
    iwa
    -0.84
    e
    -0.84
    ה
    -0.84
     Tats
    -0.82
    й
    -0.82
    paya
    -0.80
    kém
    -0.77
     Papi
    -0.77
    POSITIVE LOGITS
    ứt
    0.91
     suivie
    0.85
     Lynd
    0.84
    Халык
    0.84
     Nazareth
    0.82
    に
    0.82
    ly
    0.81
     couver
    0.81
    ab
    0.79
    adə
    0.79
    Activations Density 7.618%

    No Known Activations