© 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. 3775
    Prev
    Next
    INDEX
    Explanations

    references to threshold values used in signal detection processes

    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
    ukone
    -0.61
    pidou
    -0.60
     MonoBehaviour
    -0.59
    )}_
    -0.59
    __).
    -0.59
    SaveChanges
    -0.58
     Adven
    -0.58
    :],
    -0.57
    วด
    -0.57
    omock
    -0.57
    POSITIVE LOGITS
     threshold
    3.28
     Threshold
    2.98
    threshold
    2.95
     thresholds
    2.80
    Threshold
    2.73
    thresholds
    2.27
    THRESHOLD
    2.19
     seuil
    2.02
    阈
    2.02
    reshold
    1.79
    Activations Density 0.006%

    No Known Activations