© 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. 5-CLT-HP
    7. 3437
    Prev
    Next
    INDEX
    Explanations

    code

    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
    vidia
    -0.47
     Gra
    -0.43
     char
    -0.42
    ></
    -0.42
    ()){
    -0.42
     {
    -0.42
     i
    -0.40
    umbus
    -0.39
     Land
    -0.39
     &
    -0.39
    POSITIVE LOGITS
     дописавши
    0.91
     Bioaccumulative
    0.83
     <<<<<<<<<<<<<<
    0.83
    expandindo
    0.82
    AutoScaleMode
    0.79
     оригіналу
    0.79
     ExecuteAsync
    0.78
    Personensuche
    0.78
     صوتيه
    0.78
    ruptedException
    0.77
    Activations Density 0.002%

    No Known Activations