© 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. 679
    Prev
    Next
    INDEX
    Explanations

    the word “now” followed by pronouns or words indicating opinion or viewpoint

    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
     current
    -0.72
     Sargent
    -0.68
     EAC
    -0.68
     سبتمبر
    -0.68
    PageState
    -0.67
    getStatusCode
    -0.66
    URI
    -0.66
    UIControlState
    -0.66
     FBref
    -0.66
     Majesty
    -0.65
    POSITIVE LOGITS
     Now
    1.30
    Now
    1.29
     NOW
    1.18
    NOW
    1.13
    now
    1.12
     now
    1.11
    Теперь
    1.03
     Теперь
    1.02
     Ahora
    1.01
     теперь
    0.98
    Activations Density 0.324%

    No Known Activations