© 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. 5-CLT-HP
    7. 37
    Prev
    Next
    INDEX
    Explanations

    Describing situations

    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
     include
    -0.56
     host
    -0.56
    msgTypes
    -0.53
     hosts
    -0.52
     AssemblyTitle
    -0.51
    Royce
    -0.51
     Shiloh
    -0.50
    楽しめる
    -0.49
     propOrder
    -0.49
    rungsseite
    -0.49
    POSITIVE LOGITS
    OGND
    0.68
    ItemBackground
    0.66
    bootstrapcdn
    0.61
    WaitGroup
    0.60
    itemBuilder
    0.58
    ValueStyle
    0.55
    addGap
    0.52
    cooling
    0.51
     تضيفلها
    0.51
    progress
    0.50
    Activations Density 0.003%

    No Known Activations