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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 276
    Prev
    Next
    INDEX
    Explanations

    1

    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
    Kont
    -0.66
     Kont
    -0.63
    kont
    -0.59
    -
    -0.52
     as
    -0.52
     m
    -0.52
     door
    -0.51
    inn
    -0.50
     kont
    -0.49
     potential
    -0.49
    POSITIVE LOGITS
    utilisons
    0.61
     BoxFit
    0.60
     Majefty
    0.60
     transfieras
    0.59
     rospy
    0.58
    tvguidetime
    0.58
     preuves
    0.57
     behövs
    0.57
    DoubleQuotes
    0.57
     Efq
    0.57
    Activations Density 0.001%

    No Known Activations