© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1213
    Prev
    Next
    INDEX
    Explanations

    Clarification, self-evident statements

    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
    
    -0.77
     They
    -0.66
     kasarigan
    -0.66
     Somewhat
    -0.64
     Definitely
    -0.62
     Surely
    -0.61
    KommentareTeilen
    -0.61
    contentLoaded
    -0.60
     Certainly
    -0.59
    bootstrapcdn
    -0.59
    POSITIVE LOGITS
     to
    0.60
    culously
    0.59
     there
    0.58
    karni
    0.56
     each
    0.52
     the
    0.52
     one
    0.51
    ForTesting
    0.50
    centiles
    0.49
     in
    0.49
    Activations Density 0.009%

    No Known Activations