© 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. 0-CLT-HP
    7. 40689
    Prev
    Next
    INDEX
    Explanations

    regulation/function

    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
    rungsseite
    -0.87
     propOrder
    -0.84
     avoient
    -0.82
     engraçadas
    -0.81
    ConstraintMaker
    -0.80
     juſ
    -0.79
     quæ
    -0.75
     étoient
    -0.74
     ainfi
    -0.74
     fotografico
    -0.73
    POSITIVE LOGITS
     of
    0.59
     Sin
    0.58
     under
    0.54
     in
    0.52
     Fig
    0.52
    wan
    0.51
     to
    0.51
     at
    0.51
     Son
    0.51
     rich
    0.51
    Activations Density 0.506%

    No Known Activations