© 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. 94445
    Prev
    Next
    INDEX
    Explanations

    of

    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
    UserScript
    -0.74
    XmlEnum
    -0.58
    tagHelper
    -0.58
     nakalista
    -0.57
     disambiguazione
    -0.56
    曖昧さ回避
    -0.55
    ScopeManager
    -0.55
    fäl
    -0.53
    HtmlAttribute
    -0.51
     ineffec
    -0.51
    POSITIVE LOGITS
     a
    0.97
     an
    0.75
     any
    0.68
    édie
    0.56
     most
    0.55
     the
    0.52
     your
    0.52
    lexikon
    0.51
     fleste
    0.51
     even
    0.51
    Activations Density 0.007%

    No Known Activations