© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97522
    Prev
    Next
    INDEX
    Explanations

    Printers and general subjects

    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
     thing
    -1.07
     THING
    -0.77
    addContainerGap
    -0.67
     الحره
    -0.64
     незавершена
    -0.64
    ResponseWriter
    -0.63
     printer
    -0.61
     Thing
    -0.60
     rembourse
    -0.60
     plais
    -0.60
    POSITIVE LOGITS
    ,
    0.61
    s
    0.59
     ho
    0.59
    lust
    0.57
    ist
    0.57
    space
    0.56
     in
    0.55
     '
    0.55
    '
    0.55
     as
    0.54
    Activations Density 0.018%

    No Known Activations