© 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. 4016
    Prev
    Next
    INDEX
    Explanations

    references to gene knockouts or deletions

    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
     препратки
    -0.56
    Général
    -0.50
    RequestQueue
    -0.47
     xanh
    -0.46
    ürger
    -0.46
     msglen
    -0.46
    gdala
    -0.46
    k
    -0.45
    K
    -0.45
     Ho
    -0.44
    POSITIVE LOGITS
     knock
    3.81
    knock
    3.52
     Knock
    3.30
     knocked
    3.22
    Knock
    3.22
     knocking
    3.20
     knocks
    3.20
    kno
    2.48
     knockdown
    2.41
     knockout
    2.33
    Activations Density 0.013%

    No Known Activations