© 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. 94103
    Prev
    Next
    INDEX
    Explanations

    easy

    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
     easy
    -2.45
    easy
    -2.33
    Easy
    -2.20
     Easy
    -2.11
     easier
    -2.02
     fácil
    -1.89
     EASY
    -1.88
    easily
    -1.87
     easily
    -1.84
    EASY
    -1.81
    POSITIVE LOGITS
     to
    0.93
     pe
    0.84
     and
    0.67
    going
    0.65
     Pe
    0.64
    ,
    0.64
    est
    0.60
     (
    0.60
     on
    0.59
     as
    0.57
    Activations Density 0.061%

    No Known Activations