© 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. 0-RES-MATRYOSHKA-DC
    7. 13405
    Prev
    Next
    INDEX
    Explanations

    references to the process of releasing or secreting substances

    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
    IVEREF
    -0.47
     redor
    -0.46
    Tool
    -0.45
     cons
    -0.45
    console
    -0.45
    ramentas
    -0.44
     Tennant
    -0.43
    kega
    -0.43
    project
    -0.42
    Kira
    -0.42
    POSITIVE LOGITS
    BufferException
    0.74
    ſelf
    0.72
     uſe
    0.71
     ſmall
    0.70
    Numerade
    0.69
    ennies
    0.66
     faſt
    0.66
    icose
    0.65
     Marconi
    0.65
    Hauptartikel
    0.65
    Activations Density 0.133%

    No Known Activations