© 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. 570
    Prev
    Next
    INDEX
    Explanations

    titles, specifically "Mr." followed by a period.

    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
    DispatchToProps
    -0.65
    ukone
    -0.62
     confirmé
    -0.60
    spender
    -0.59
    RetentionPolicy
    -0.59
     recevrez
    -0.59
     peine
    -0.58
    toggler
    -0.57
    WindowConstants
    -0.56
    RectangleBorder
    -0.55
    POSITIVE LOGITS
     Mr
    1.59
    Mr
    1.45
     Mister
    1.31
     mr
    1.26
     Mrs
    1.20
     Ms
    1.20
    Mister
    1.16
    Mrs
    1.10
     Monsieur
    1.09
    Ms
    1.02
    Activations Density 0.135%

    No Known Activations