© 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. 2-RES-MATRYOSHKA-DC
    7. 6328
    Prev
    Next
    INDEX
    Explanations

    mentions of memory addresses or pointers

    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
    AndEndTag
    -0.59
     Sosa
    -0.52
    meto
    -0.51
    BeforeMethod
    -0.51
     bero
    -0.50
     pensieri
    -0.50
    ISMO
    -0.50
    랫
    -0.50
     pouce
    -0.49
    BOD
    -0.49
    POSITIVE LOGITS
     uintptr
    5.22
    uintptr
    1.16
    #+#
    0.77
     uLocal
    0.73
    MLLoader
    0.73
    ReusableCell
    0.72
    
    0.72
    quelize
    0.71
     NSCoder
    0.71
     indisponible
    0.70
    Activations Density 0.002%

    No Known Activations