© 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. 0-CLT-HP
    7. 40477
    Prev
    Next
    INDEX
    Explanations

    analy

    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
     Analy
    -0.72
    bootstrapcdn
    -0.66
    ParallelGroup
    -0.65
    ToScroll
    -0.63
    mybatisplus
    -0.62
    errHandler
    -0.59
     TestBed
    -0.58
    OGND
    -0.57
    QMetaType
    -0.57
    Література
    -0.57
    POSITIVE LOGITS
    ed
    0.75
     getCity
    0.52
    paksa
    0.51
     ब्रेकडाउन
    0.50
     navideña
    0.47
    ഔ
    0.47
    ised
    0.46
     pratique
    0.45
     navideño
    0.45
    ็จ
    0.44
    Activations Density 0.037%

    No Known Activations