© 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. 5095
    Prev
    Next
    INDEX
    Explanations

    dates or years

    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
     setMessage
    -0.57
     frattempo
    -0.56
     }}"></
    -0.53
    มาะ
    -0.50
    Maße
    -0.50
     antaranya
    -0.50
    WindowConstants
    -0.50
    +#+
    -0.48
    ThroughAttribute
    -0.47
     fallu
    -0.47
    POSITIVE LOGITS
    onViewCreated
    0.71
    Personensuche
    0.50
    WebVitals
    0.50
    Gambas
    0.48
     насеље
    0.48
    abestanden
    0.47
    VersionUID
    0.47
     GlobalKey
    0.47
     Cade
    0.46
    atief
    0.46
    Activations Density 0.001%

    No Known Activations