© 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. 12297
    Prev
    Next
    INDEX
    Explanations

    references to endogenous factors involved in biochemical and molecular processes, particularly those related to endogenous substances and regulatory mechanisms

    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
    :^(
    -0.59
    рующие
    -0.49
     sanat
    -0.49
    cimento
    -0.48
     död
    -0.47
    Kaieteur
    -0.46
    çe
    -0.46
    Sustain
    -0.45
     naturally
    -0.45
     ponú
    -0.45
    POSITIVE LOGITS
     endogenous
    2.55
    rungsseite
    0.84
    RenderAtEndOf
    0.78
    Билгалдахарш
    0.67
     Sleeps
    0.65
     referenties
    0.63
     архивлан
    0.62
    ogenous
    0.60
    ngrx
    0.60
    цездатний
    0.59
    Activations Density 0.001%

    No Known Activations