© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93035
    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
    Numerology
    -0.71
     disambiguazione
    -0.63
    atorics
    -0.62
    enderror
    -0.60
    Demografie
    -0.56
    Geplaatst
    -0.54
     AssemblyCulture
    -0.53
    |()
    -0.53
    LEncoder
    -0.49
    OKING
    -0.49
    POSITIVE LOGITS
    illoin
    0.60
     them
    0.60
     المعيارى
    0.56
     such
    0.55
    heira
    0.50
     défis
    0.50
     thèse
    0.49
    LLocation
    0.48
     näin
    0.48
     lemn
    0.47
    Activations Density 0.003%

    No Known Activations