© 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. 7146
    Prev
    Next
    INDEX
    Explanations

    references to the concept 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
     precisely
    -1.16
    Precise
    -0.84
     Precise
    -0.83
    precise
    -0.80
     precisamente
    -0.76
     précisément
    -0.73
    Precision
    -0.67
     Careful
    -0.63
     precision
    -0.62
    precision
    -0.62
    POSITIVE LOGITS
     exact
    1.73
    exact
    1.70
     Exact
    1.67
    Exact
    1.37
     EXACT
    1.13
     exacte
    1.05
     exacta
    0.71
     exacto
    0.69
    EXACT
    0.65
     approximate
    0.64
    Activations Density 0.009%

    No Known Activations