© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 798
    Prev
    Next
    INDEX
    Explanations

    words relating to study evaluations and assessments

    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
     claim
    -0.57
     record
    -0.57
     wy
    -0.57
    er
    -0.56
    record
    -0.56
     nuage
    -0.56
     boast
    -0.56
     Vorschlag
    -0.56
    闻
    -0.54
    geon
    -0.54
    POSITIVE LOGITS
     evaluated
    1.74
     evaluate
    1.73
     evaluating
    1.66
     evaluates
    1.63
     assessing
    1.60
    evaluated
    1.60
     assessed
    1.58
     Evalu
    1.56
     Evaluating
    1.56
     evalu
    1.55
    Activations Density 0.683%

    No Known Activations