© 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. 184
    Prev
    Next
    INDEX
    Explanations

    Code/Programming

    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
    Personendaten
    -0.97
     Roskov
    -0.97
     '\\;'
    -0.93
     disambiguazione
    -0.90
     kasarigan
    -0.88
    Jeografia
    -0.86
    SourceChecksum
    -0.84
    NameInMap
    -0.84
     дописавши
    -0.83
     betweenstory
    -0.78
    POSITIVE LOGITS
     simpler
    0.39
     Träger
    0.38
     jäm
    0.37
     ordinary
    0.35
     simple
    0.35
    astrous
    0.34
    enumi
    0.34
     típicos
    0.33
     ordinaire
    0.33
    vrier
    0.33
    Activations Density 0.003%

    No Known Activations