© 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. 3-RES-MATRYOSHKA-DC
    7. 2640
    Prev
    Next
    INDEX
    Explanations

    the word "accuracy"

    oai_token-act-pair · gemini-2.0-flash
    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
     exactly
    -0.88
    exactly
    -0.80
     exatamente
    -0.73
     Exactly
    -0.72
     exact
    -0.71
    Exactly
    -0.71
     exactement
    -0.69
     exactamente
    -0.66
    EXACT
    -0.66
     esattamente
    -0.64
    POSITIVE LOGITS
     accuracy
    2.61
     Accuracy
    2.48
    Accuracy
    2.34
    accuracy
    2.20
     ACCUR
    1.92
     Accurate
    1.85
     accurate
    1.84
    Accurate
    1.82
    accurate
    1.78
     inaccuracy
    1.72
    Activations Density 0.030%

    No Known Activations