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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93923
    Prev
    Next
    INDEX
    Explanations

    Descriptive/technical writing

    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
    ttino
    -0.55
    __':
    -0.51
    giar
    -0.50
    pertise
    -0.48
     curfew
    -0.47
    Viitteet
    -0.47
    parole
    -0.47
     ultrasonic
    -0.47
    QApplication
    -0.46
     supernatant
    -0.46
    POSITIVE LOGITS
     consultato
    0.61
     &___
    0.59
    dafx
    0.59
     мәкал
    0.56
     referred
    0.54
     saites
    0.53
     autorytatywna
    0.53
     ujednoznacz
    0.53
     disambiguazione
    0.52
     described
    0.52
    Activations Density 0.007%

    No Known Activations