© 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. 1-CLT-HP
    7. 14591
    Prev
    Next
    INDEX
    Explanations

    dollar sign

    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
     $
    -0.64
     Den
    -0.59
     money
    -0.57
     Cole
    -0.57
     Money
    -0.57
     Dan
    -0.57
     Di
    -0.57
     DEN
    -0.56
     IF
    -0.56
     IN
    -0.55
    POSITIVE LOGITS
     bénéfices
    0.54
     écl
    0.53
     dieux
    0.51
    ябре
    0.49
     enfans
    0.49
    ńczy
    0.49
     flesta
    0.47
    1
    0.47
     незавершена
    0.46
    AnchorStyles
    0.45
    Activations Density 0.009%

    No Known Activations