© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2544
    Prev
    Next
    INDEX
    Explanations

    associates

    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
    UrlResolution
    -0.67
    #
    -0.64
     Paglinawan
    -0.62
    ništ
    -0.61
    argout
    -0.59
    abetes
    -0.57
    ungsbedingungen
    -0.54
     '\\;'
    -0.54
    ratie
    -0.52
     onCancelled
    -0.52
    POSITIVE LOGITS
    uxxxx
    0.46
    liber
    0.46
     monit
    0.45
    Liber
    0.45
    topics
    0.44
    Aliens
    0.44
     liên
    0.43
    ylon
    0.43
     мета
    0.43
    thodox
    0.43
    Activations Density 0.002%

    No Known Activations