© 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. 944
    Prev
    Next
    INDEX
    Explanations

    references to assessment or evaluation activities

    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
    EXPERIMENT
    -0.62
     wyniki
    -0.61
    Experiments
    -0.61
     coba
    -0.60
    EXPERIMENTAL
    -0.59
    theorem
    -0.59
    Experiment
    -0.59
    onView
    -0.57
    experiment
    -0.56
    чах
    -0.56
    POSITIVE LOGITS
     assessment
    3.47
     Assessment
    3.38
     assess
    3.25
     assessments
    3.22
     assessed
    3.20
    Assessment
    3.16
     ASSESSMENT
    3.11
     Assessments
    3.08
     assessing
    3.06
    assess
    3.06
    Activations Density 0.104%

    No Known Activations