© 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. 6-RES-MATRYOSHKA-DC
    7. 723
    Prev
    Next
    INDEX
    Explanations

    the word "observe" or its variants

    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
    templateUrl
    -0.75
     []).
    -0.66
     çerçe
    -0.63
    ▒
    -0.60
    CJK
    -0.59
    retty
    -0.59
    }`).
    -0.59
    @[+][
    -0.57
    </td>
    -0.57
    www
    -0.57
    POSITIVE LOGITS
     observed
    1.86
     Observations
    1.86
     OBSERV
    1.84
     Observed
    1.84
     Observation
    1.82
    observations
    1.82
     observation
    1.80
     observations
    1.80
    observed
    1.79
    Observations
    1.78
    Activations Density 0.158%

    No Known Activations