© 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. 5990
    Prev
    Next
    INDEX
    Explanations

    situations or statements emphasizing that something is entirely or utterly the case

    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
    full
    -0.94
     full
    -0.91
     Full
    -0.81
     complete
    -0.80
    complete
    -0.77
    Full
    -0.76
    FULL
    -0.75
     peł
    -0.69
    いかが
    -0.69
     EconPapers
    -0.68
    POSITIVE LOGITS
     completely
    2.80
     Completely
    2.63
    Completely
    2.50
    completely
    2.48
     entirely
    2.44
     totally
    2.42
     Totally
    2.19
    totally
    2.14
    Totally
    2.11
     completamente
    2.05
    Activations Density 0.115%

    No Known Activations