© 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. 718
    Prev
    Next
    INDEX
    Explanations

    immediacy

    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
    TagMode
    -0.72
     start
    -0.63
    WireFormatLite
    -0.58
    /**
    -0.58
    CloseOperation
    -0.57
    IVEREF
    -0.57
    __':
    -0.56
     starts
    -0.55
    |}{}
    -0.55
    ÁND
    -0.55
    POSITIVE LOGITS
    .
    0.87
     picioare
    0.68
     vermelhas
    0.59
     femininas
    0.57
     sociaux
    0.57
     världen
    0.56
     faciles
    0.55
     supplémentaires
    0.55
     artificiales
    0.55
     colorés
    0.54
    Activations Density 0.001%

    No Known Activations