© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1626
    Prev
    Next
    INDEX
    Explanations

    clog

    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
     Paglinawan
    -1.13
    tvguidetime
    -1.09
    WebVitals
    -1.07
     المعيارى
    -1.06
     ProtoMessage
    -0.95
    bewerken
    -0.94
     feroit
    -0.94
    verwijspagina
    -0.91
    
    -0.91
    GEBURTSDATUM
    -0.90
    POSITIVE LOGITS
    s
    1.13
    t
    1.07
    n
    0.86
    d
    0.86
    r
    0.81
    m
    0.81
    a
    0.80
    g
    0.77
    k
    0.76
    sy
    0.73
    Activations Density 0.051%

    No Known Activations