© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5234
    Prev
    Next
    INDEX
    Explanations

    references to licensing status or permissions

    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
    WithFormat
    -0.74
    WaitGroup
    -0.63
    ClCompile
    -0.57
    Moved
    -0.52
     Moved
    -0.52
    BindView
    -0.50
     تانيه
    -0.49
     hinter
    -0.48
     INCLUD
    -0.48
    dificio
    -0.48
    POSITIVE LOGITS
     authorized
    2.13
     authorised
    2.11
     licensed
    1.81
     Authorized
    1.77
    authorized
    1.73
     Licensed
    1.59
    authorised
    1.56
     certified
    1.55
     accredited
    1.55
     approved
    1.53
    Activations Density 0.115%

    No Known Activations