© 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. 20-CLT-HP
    7. 76317
    Prev
    Next
    INDEX
    Explanations

    technology/data

    np_max-act-logits · 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
     fédé
    -0.62
     Chickens
    -0.60
    (!__
    -0.59
     Rabbits
    -0.59
    Robots
    -0.57
     chré
    -0.56
     Dinosaurs
    -0.54
    WithIOException
    -0.54
    tonode
    -0.54
     تانيه
    -0.54
    POSITIVE LOGITS
    তথ্যসূত্র
    0.52
    ValueGenerated
    0.47
    GenerationType
    0.47
    <bos>
    0.46
    shadowOpacity
    0.45
    tabilis
    0.45
     kasarigan
    0.44
    ValueStyle
    0.44
     Ans
    0.44
    vierung
    0.43
    Activations Density 0.000%

    No Known Activations