© 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. 0-CLT-HP
    7. 42490
    Prev
    Next
    INDEX
    Explanations

    -ing verbs

    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
    bootstrapcdn
    -0.49
     مرئيه
    -0.46
     useAppContext
    -0.44
    dotenv
    -0.42
     pinulongan
    -0.42
     ahol
    -0.41
     sua
    -0.41
    orological
    -0.40
    DataAnnotations
    -0.40
    sspiel
    -0.40
    POSITIVE LOGITS
     myſelf
    0.91
    ſelf
    0.89
     Anſ
    0.81
     Efq
    0.81
     Theſe
    0.79
    ſelves
    0.79
     Monfieur
    0.77
     Jefus
    0.77
     fubject
    0.75
     itſelf
    0.75
    Activations Density 0.237%

    No Known Activations