© 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. 14244
    Prev
    Next
    INDEX
    Explanations

    patterns involving specific numerical identifiers and labels associated with datasets and genetic variants

    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
    styleable
    -0.51
    UserScript
    -0.50
    ruptedException
    -0.49
    ecal
    -0.48
     Mak
    -0.47
    اد
    -0.46
    zik
    -0.46
    opie
    -0.45
    ankar
    -0.45
     pasto
    -0.45
    POSITIVE LOGITS
    KD
    2.91
     KD
    2.38
    kd
    2.25
     kd
    1.90
    Kd
    1.23
     Roskov
    0.79
     NSCoder
    0.78
    Geplaatst
    0.77
    HtmlAttribute
    0.75
    RetentionPolicy
    0.69
    Activations Density 0.001%

    No Known Activations