© 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. 275
    Prev
    Next
    INDEX
    Explanations

    the

    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
    AttributeSet
    -0.47
    InvalidProtocol
    -0.46
     control
    -0.46
     hỏi
    -0.43
    Compl
    -0.42
    Mait
    -0.42
    lm
    -0.41
    屠
    -0.41
     Control
    -0.41
    enuta
    -0.41
    POSITIVE LOGITS
    Personendaten
    0.73
    AndEndTag
    0.69
    PreferredItem
    0.68
     oprot
    0.65
    يميديا
    0.64
     betweenstory
    0.63
     ujednoznacz
    0.62
     <>",
    0.61
     viewDidLoad
    0.61
    WireFormatLite
    0.60
    Activations Density 0.006%

    No Known Activations