© 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. 20-CLT-HP
    7. 77437
    Prev
    Next
    INDEX
    Explanations

    delivery

    np_max-act-logits · 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
    AndEndTag
    -0.70
    Personendaten
    -0.70
    SequentialGroup
    -0.60
     Chwiliwch
    -0.57
     nonatomic
    -0.57
     CWE
    -0.56
     jsPsych
    -0.56
    naments
    -0.56
     invokingState
    -0.56
     heuer
    -0.55
    POSITIVE LOGITS
     delivery
    0.70
     Delivery
    0.66
     self
    0.66
     Door
    0.64
     Deliver
    0.59
     Bird
    0.56
    Delivery
    0.56
     Way
    0.56
     DELIVERY
    0.54
     Self
    0.53
    Activations Density 0.000%

    No Known Activations