© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41908
    Prev
    Next
    INDEX
    Explanations

    interest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interest
    -1.64
     Interest
    -1.47
    Interest
    -1.41
    interest
    -1.38
     patient
    -1.10
     INTEREST
    -1.09
     interés
    -1.06
    intérêt
    -1.04
     interests
    -0.98
     interesse
    -0.94
    POSITIVE LOGITS
     complained
    0.53
     inside
    0.49
    inside
    0.47
     propre
    0.47
    wnątrz
    0.46
     wherever
    0.45
    ّد
    0.44
    力的
    0.44
     notified
    0.44
    receiving
    0.43
    Activations Density 0.090%

    No Known Activations