© 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. 5291
    Prev
    Next
    INDEX
    Explanations

    references to specific named entities, locations, or specialized technical terms

    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
     λ
    -1.28
    lambda
    -1.16
    λ
    -0.92
     Weston
    -0.84
     Lamb
    -0.82
     Lawson
    -0.80
     lambda
    -0.79
    czaj
    -0.78
     Jackson
    -0.75
     Arp
    -0.75
    POSITIVE LOGITS
    __*/
    1.13
     Rollins
    1.05
    IMPORTED
    0.93
     Baile
    0.88
     Reinhold
    0.88
     Schlä
    0.86
     Balboa
    0.84
     OMIT
    0.83
     Roca
    0.82
     Stras
    0.82
    Activations Density 1.836%

    No Known Activations