© 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. 1-CLT-HP
    7. 14275
    Prev
    Next
    INDEX
    Explanations

    oid

    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
     Frequent
    -0.55
    Frequent
    -0.54
    
    -0.52
     Pollack
    -0.51
     frequent
    -0.49
    لیسی
    -0.49
    itana
    -0.49
    frequent
    -0.48
    NST
    -0.48
    Collapse
    -0.48
    POSITIVE LOGITS
    +#+#
    0.76
    dersfield
    0.64
    WebControls
    0.59
    ̣t
    0.56
    ‍♀️
    0.54
     Hiz
    0.54
     Xunit
    0.53
    hält
    0.50
     Vite
    0.50
    endpush
    0.50
    Activations Density 0.021%

    No Known Activations