© 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. 1-RES-MATRYOSHKA-DC
    7. 366
    Prev
    Next
    INDEX
    Explanations

    references to statistical measures of precision or accuracy

    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
    loat
    -0.62
    '},
    -0.57
     often
    -0.55
     idea
    -0.54
    '):
    -0.54
    ...',
    -0.53
    ++
    -0.52
     llan
    -0.51
     baffling
    -0.50
     examin
    -0.50
    POSITIVE LOGITS
     respectively
    4.72
    respectively
    4.25
     respectivamente
    3.91
     respectivement
    3.31
     respective
    2.70
     соответственно
    2.52
     rispet
    2.47
     respec
    2.19
     respectivos
    2.11
    respective
    2.09
    Activations Density 1.270%

    No Known Activations