© 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. 1908
    Prev
    Next
    INDEX
    Explanations

    q

    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
    f
    -0.94
    q
    -0.93
    v
    -0.77
    b
    -0.75
    c
    -0.71
    n
    -0.68
    m
    -0.67
    p
    -0.67
    x
    -0.67
    k
    -0.66
    POSITIVE LOGITS
     Jefus
    1.13
     myſelf
    1.05
     itſelf
    1.01
     estekak
    0.96
     himſelf
    0.96
    IntoConstraints
    0.94
    DockStyle
    0.93
     purpoſe
    0.92
     Monfieur
    0.92
     themſelves
    0.89
    Activations Density 0.347%

    No Known Activations