© 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. 493
    Prev
    Next
    INDEX
    Explanations

    occurrences of positive evaluations or indicators of quality

    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
    Larger
    -0.72
     Efq
    -0.72
     nonatomic
    -0.66
     Larger
    -0.65
    Smaller
    -0.65
     ISNI
    -0.65
     Smaller
    -0.63
    larger
    -0.63
    antlr
    -0.62
     larger
    -0.61
    POSITIVE LOGITS
     good
    2.78
    good
    2.50
     excellent
    2.25
    Good
    2.19
     Good
    2.16
     GOOD
    2.13
    excellent
    2.08
     better
    2.02
    GOOD
    2.02
     well
    1.93
    Activations Density 2.878%

    No Known Activations