© 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. 0-CLT-HP
    7. 42115
    Prev
    Next
    INDEX
    Explanations

    CFS

    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
     myſelf
    -1.05
     Monfieur
    -1.00
     becauſe
    -0.97
     Efq
    -0.96
     itſelf
    -0.95
     Theſe
    -0.95
     themſelves
    -0.93
     purpoſe
    -0.92
     himſelf
    -0.91
     Anſ
    -0.91
    POSITIVE LOGITS
     retenir
    0.54
    s
    0.45
    िखित
    0.43
    имость
    0.41
    ly
    0.40
    ть
    0.40
     of
    0.39
     in
    0.39
     R
    0.37
    tid
    0.36
    Activations Density 0.130%

    No Known Activations