© 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. 6-RES-MATRYOSHKA-DC
    7. 749
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
     Normdatei
    -0.73
    userdetails
    -0.66
    LabelTagHelper
    -0.64
    photobucket
    -0.63
    extAlignment
    -0.63
    FormTagHelper
    -0.63
    MessageState
    -0.63
     Meksiku
    -0.60
    NOPQRST
    -0.60
     MainAxisSize
    -0.59
    POSITIVE LOGITS
    GEBURTSDATUM
    0.67
    Lähteet
    0.52
    ="@+
    0.52
    πως
    0.52
    ngdoc
    0.52
    scalatest
    0.51
    Искәрмәләр
    0.49
     урна
    0.49
     елның
    0.47
     kasarigan
    0.47
    Activations Density 2.579%

    No Known Activations