© 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. 4-CLT-HP
    7. 3043
    Prev
    Next
    INDEX
    Explanations

    programming/technical documentation

    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
    awtextra
    -0.69
     put
    -0.52
     affinch
    -0.49
    ArgumentParser
    -0.47
     Put
    -0.45
     Putting
    -0.45
     Tried
    -0.44
    Put
    -0.44
     afin
    -0.43
     setLoading
    -0.41
    POSITIVE LOGITS
    CloseOperation
    0.70
     propOrder
    0.67
    TargetException
    0.61
     silhouettes
    0.61
    izontal
    0.57
     sherds
    0.57
    unknownFields
    0.57
    GeneratedValue
    0.56
     synthase
    0.56
    providedIn
    0.56
    Activations Density 0.004%

    No Known Activations