© 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. 6589
    Prev
    Next
    INDEX
    Explanations

    references to conditional independence statements or conditions in probabilistic and statistical contexts

    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
     bezeichneter
    -0.87
    hdashline
    -0.73
    Tus
    -0.65
     Kea
    -0.64
     IMDG
    -0.64
    invokeLater
    -0.63
    LLocation
    -0.63
     Âge
    -0.62
    stdc
    -0.61
    KeySpec
    -0.61
    POSITIVE LOGITS
     conditional
    1.72
     Conditional
    1.57
    conditional
    1.51
    Conditional
    1.46
     conditionally
    1.40
     deterministic
    1.20
    conditionally
    1.19
     stochastic
    1.18
     unconditional
    1.15
    chastic
    1.09
    Activations Density 0.284%

    No Known Activations