© 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. 5-CLT-HP
    7. 3914
    Prev
    Next
    INDEX
    Explanations

    convenient functionality/code filler

    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
     convenience
    -0.62
     convenient
    -0.58
    Convenient
    -0.54
     Convenient
    -0.54
     Ease
    -0.50
    GeneratedMessage
    -0.49
     facilité
    -0.46
    ease
    -0.45
    Facile
    -0.45
     ease
    -0.45
    POSITIVE LOGITS
    MLLoader
    0.72
    bootstrapcdn
    0.66
     الدولى
    0.61
    audiovisuel
    0.59
    eseorang
    0.58
    encodeWith
    0.57
     CURIAM
    0.56
    הערות
    0.56
    postIndex
    0.55
    driver
    0.54
    Activations Density 0.010%

    No Known Activations