© 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. 4590
    Prev
    Next
    INDEX
    Explanations

    quotations

    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
     cascades
    -0.54
     uska
    -0.51
     Nia
    -0.50
    opla
    -0.47
     cascade
    -0.47
    
    -0.47
     Virginie
    -0.46
     operational
    -0.45
     lunar
    -0.44
    centerTitle
    -0.43
    POSITIVE LOGITS
     WaitForSeconds
    0.59
     Meksika
    0.59
    utives
    0.58
    <()>
    0.58
    ppuden
    0.57
    ELTS
    0.57
    hassee
    0.56
    phrag
    0.56
     Walkover
    0.56
    photobucket
    0.54
    Activations Density 0.002%

    No Known Activations