© 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. 1-CLT-HP
    7. 372
    Prev
    Next
    INDEX
    Explanations

    fixation

    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
    iség
    -0.58
    étrie
    -0.54
    verwijspagina
    -0.53
    èlement
    -0.52
     CURIAM
    -0.52
    Persistent
    -0.51
    wahati
    -0.48
    منبع
    -0.47
    бражение
    -0.47
    persistent
    -0.47
    POSITIVE LOGITS
    
    0.72
    ⓧ
    0.59
     estekak
    0.56
     atrocities
    0.54
    ApplicationTests
    0.54
    XmlAccessType
    0.54
    pyx
    0.54
    aarrggbb
    0.53
    TableAdapter
    0.50
    ChildScrollView
    0.50
    Activations Density 0.051%

    No Known Activations