© 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. 45594
    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
    Personendaten
    -0.69
     ModelExpression
    -0.56
    reportWebVitals
    -0.52
     ligiloj
    -0.51
    তথ্যসূত্র
    -0.51
    arynge
    -0.50
    thargy
    -0.50
    HomeAsUpEnabled
    -0.50
     AssemblyCulture
    -0.50
    Viitteet
    -0.49
    POSITIVE LOGITS
    ]='\
    0.62
     ModelRenderer
    0.57
    izr
    0.57
     Chwiliwch
    0.57
    AsUp
    0.55
    JsonInclude
    0.55
     FontFamily
    0.54
    CloseOperation
    0.54
    __((
    0.54
     }}"
    0.54
    Activations Density 0.063%

    No Known Activations