© 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. 4298
    Prev
    Next
    INDEX
    Explanations

    references to specific correction factors or adjustments, particularly related to scientific calculations or measurements

    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
     properly
    -0.71
     correctly
    -0.70
     proper
    -0.68
     PROPER
    -0.65
     правильно
    -0.65
    properly
    -0.61
     cog
    -0.59
     wrong
    -0.57
     Proper
    -0.56
    proper
    -0.56
    POSITIVE LOGITS
     correction
    2.72
     Correction
    2.61
     corrections
    2.53
    correction
    2.39
     Corrections
    2.23
     CORRE
    2.16
    Correction
    2.05
    Corre
    1.96
    corre
    1.80
     corrected
    1.79
    Activations Density 0.036%

    No Known Activations