© 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. 0-RES-MATRYOSHKA-DC
    7. 14981
    Prev
    Next
    INDEX
    Explanations

    references to a specific person

    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
     what
    -0.68
    ための
    -0.60
     part
    -0.52
     mga
    -0.52
    ために
    -0.51
    Log
    -0.50
     stringBy
    -0.50
     or
    -0.49
    gelijk
    -0.48
     free
    -0.48
    POSITIVE LOGITS
     صوتيه
    0.97
    GraphicsUnit
    0.85
    MemoryWarning
    0.84
     للاسماء
    0.84
    AnchorStyles
    0.79
    StoryboardSegue
    0.77
     CreateTagHelper
    0.75
    InjectAttribute
    0.73
     Whilst
    0.72
    principalTable
    0.71
    Activations Density 0.021%

    No Known Activations