© 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. 0-CLT-HP
    7. 90807
    Prev
    Next
    INDEX
    Explanations

    Mysteries

    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
     houſe
    -0.76
     exploits
    -0.69
     captures
    -0.66
    nts
    -0.65
    nt
    -0.64
     Houſe
    -0.64
    UNT
    -0.61
     Negroes
    -0.60
    AsUp
    -0.59
     cauſe
    -0.59
    POSITIVE LOGITS
     disambiguazione
    0.71
     biografias
    0.63
    AddHtmlAttribute
    0.61
     AssemblyProduct
    0.60
     TextAlign
    0.60
    Ӏ
    0.58
    الإنجليزية
    0.56
    довлет
    0.56
    addGap
    0.56
    sieurs
    0.55
    Activations Density 0.053%

    No Known Activations