© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95080
    Prev
    Next
    INDEX
    Explanations

    fee

    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
     fees
    -1.08
     fee
    -1.03
     Planet
    -0.86
    fee
    -0.79
    Fees
    -0.77
    Fee
    -0.75
     Fees
    -0.74
     Fee
    -0.71
     FEES
    -0.70
    Planet
    -0.69
    POSITIVE LOGITS
     الحره
    1.01
    IntoConstraints
    0.94
     Normdatei
    0.84
     defaultstate
    0.78
     purpoſe
    0.78
    RectangleBorder
    0.78
     pleaſure
    0.77
    存于互联网档案馆
    0.77
    ftagPool
    0.77
     Majefty
    0.76
    Activations Density 0.246%

    No Known Activations