© 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. 2011
    Prev
    Next
    INDEX
    Explanations

    the word "interest"

    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
    opje
    -0.75
    mago
    -0.65
    — 
    -0.65
     nélk
    -0.64
    wahati
    -0.64
    lawless
    -0.64
    neté
    -0.64
     Bradshaw
    -0.63
    ophanes
    -0.61
    Xaml
    -0.58
    POSITIVE LOGITS
     interest
    3.81
     Interest
    3.58
    interest
    3.44
    Interest
    3.41
     INTEREST
    3.39
     interests
    3.33
    INTEREST
    3.03
     Interests
    3.02
    interests
    2.81
    Interests
    2.59
    Activations Density 0.212%

    No Known Activations