© 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. 10953
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical values or measurements, particularly related to blood pressure and other physiological metrics

    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
    apeno
    -0.59
    UPAC
    -0.58
    riction
    -0.58
    regation
    -0.57
    ցված
    -0.57
     Kram
    -0.56
    Explicación
    -0.54
    SequentialGroup
    -0.53
    euvres
    -0.53
    niająca
    -0.53
    POSITIVE LOGITS
     symb
    1.90
     symbiotic
    1.54
    symb
    1.46
     Symb
    1.45
    Symb
    1.21
    untu
    1.18
     consortium
    0.89
     mushroom
    0.89
     mushrooms
    0.85
     Consortium
    0.77
    Activations Density 0.002%

    No Known Activations