© 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. 4-CLT-HP
    7. 4500
    Prev
    Next
    INDEX
    Explanations

    passive voice

    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
     rarely
    -1.10
     seldom
    -1.09
     Rarely
    -1.02
     often
    -1.01
    often
    -0.97
     Often
    -0.96
     rarement
    -0.96
     spesso
    -0.93
    Often
    -0.92
     usually
    -0.90
    POSITIVE LOGITS
    ̍t
    0.54
    VersionUID
    0.52
    setupUi
    0.51
    دانشنامهٔ
    0.50
    白石
    0.48
    fäl
    0.47
     gestorben
    0.47
    Effec
    0.45
    本次
    0.45
    InputModule
    0.45
    Activations Density 0.008%

    No Known Activations