© 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. 2490
    Prev
    Next
    INDEX
    Explanations

    the word "assessment"

    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
     investigated
    -0.76
     probe
    -0.72
     investigate
    -0.67
     explored
    -0.67
     examined
    -0.65
     probed
    -0.65
     Investigation
    -0.62
     subpoena
    -0.62
     investigates
    -0.62
    examined
    -0.61
    POSITIVE LOGITS
     assessment
    2.13
     Assessment
    2.13
     assessments
    2.09
     Assessments
    2.02
     ASSESSMENT
    1.98
    Assessment
    1.94
    assessment
    1.94
    assess
    1.90
     Assess
    1.84
     assess
    1.83
    Activations Density 0.023%

    No Known Activations