© 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. 1-RES-MATRYOSHKA-DC
    7. 1191
    Prev
    Next
    INDEX
    Explanations

    references to the concept of experiencing or having experienced something repeatedly

    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
     متعلقه
    -0.66
    EndContext
    -0.63
    Unfortunately
    -0.59
     tạm
    -0.58
    లాలు
    -0.57
    pani
    -0.56
     defaultstate
    -0.56
    Facades
    -0.56
     Pristupljeno
    -0.56
     unfortunately
    -0.55
    POSITIVE LOGITS
     ever
    3.94
     never
    3.53
     EVER
    3.31
     Never
    3.30
    ever
    3.28
    never
    3.23
    Never
    3.20
     Ever
    3.13
    Ever
    3.02
     NEVER
    3.00
    Activations Density 0.050%

    No Known Activations