© 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. 2290
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers representing URLs or DOI identifiers

    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
    ánto
    -0.53
     wpis
    -0.53
     Kalt
    -0.50
     Rico
    -0.49
    schul
    -0.49
    Einsatz
    -0.49
    zean
    -0.49
    曖昧さ回避
    -0.47
    ETIES
    -0.47
     omnes
    -0.46
    POSITIVE LOGITS
    Datuak
    0.83
     nahilalakip
    0.80
    UnusedPrivate
    0.75
     StatefulWidget
    0.72
     SqlConnection
    0.71
    ScopeManager
    0.70
    بوابة
    0.69
     CreateTagHelper
    0.69
    IsContent
    0.68
    UIControlState
    0.68
    Activations Density 0.085%

    No Known Activations