© 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. 4-CLT-HP
    7. 4748
    Prev
    Next
    INDEX
    Explanations

    2

    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
    LookAnd
    -0.59
    XmlAccessType
    -0.54
    styleType
    -0.51
    BufferException
    -0.48
    UnknownFieldSet
    -0.47
    kker
    -0.45
    awt
    -0.44
     lega
    -0.44
    ihnachten
    -0.44
    ggia
    -0.44
    POSITIVE LOGITS
    ंदीखरीदारी
    0.74
    tvguidetime
    0.66
     CreateTagHelper
    0.60
     isNameExpr
    0.58
    ViewById
    0.57
    MENAFN
    0.56
     thermoc
    0.54
     censiti
    0.54
    WaitGroup
    0.54
    ()?;
    0.54
    Activations Density 0.002%

    No Known Activations