© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45507
    Prev
    Next
    INDEX
    Explanations

    news, legal documents

    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
     residents
    -1.30
     Residents
    -1.05
    Residents
    -1.02
    residents
    -0.96
     residentes
    -0.83
    lids
    -0.74
     Morris
    -0.69
     resident
    -0.68
     فريبيس
    -0.65
    +:+
    -0.63
    POSITIVE LOGITS
    InputTagHelper
    0.68
     Psyche
    0.63
    ApiModelProperty
    0.62
     Obispo
    0.58
     Nelle
    0.56
    ValueGenerated
    0.56
    setupUi
    0.56
     Blame
    0.56
    ]")]
    0.55
     Blaise
    0.55
    Activations Density 0.100%

    No Known Activations