© 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. 5-CLT-HP
    7. 92450
    Prev
    Next
    INDEX
    Explanations

    transmitting data

    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
     оригіналу
    -0.64
    Erreferentziak
    -0.61
    tagHelperRunner
    -0.59
     تضيفلها
    -0.58
     kampung
    -0.51
    dropIfExists
    -0.51
    सन्दर्भ
    -0.51
    ագրություններ
    -0.50
     تانيه
    -0.48
     africains
    -0.47
    POSITIVE LOGITS
     spurs
    0.60
     referenties
    0.60
    Dislikes
    0.55
    ]")]
    0.55
    XmlEnum
    0.54
     AssemblyTitle
    0.53
     xlink
    0.53
     servo
    0.52
    commander
    0.50
     galvan
    0.50
    Activations Density 0.001%

    No Known Activations