© 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. 1-CLT-HP
    7. 864
    Prev
    Next
    INDEX
    Explanations

    is

    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
    marle
    -0.43
    ուն
    -0.41
     rudely
    -0.40
     consecutively
    -0.40
    笔
    -0.40
     mahdol
    -0.39
     alternately
    -0.38
    canestro
    -0.38
    s
    -0.38
    富
    -0.38
    POSITIVE LOGITS
    interopRequire
    0.78
     it
    0.77
     kasarigan
    0.70
    InstanceState
    0.65
    iastes
    0.64
    ]")]
    0.63
    StructEnd
    0.61
     BoxDecoration
    0.60
    Gweler
    0.57
     InputDecoration
    0.57
    Activations Density 0.054%

    No Known Activations