© 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. 2424
    Prev
    Next
    INDEX
    Explanations

    previous

    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
     LoginForm
    -0.51
     referenties
    -0.47
     former
    -0.47
    
    -0.47
     professional
    -0.45
    ηγ
    -0.44
     form
    -0.43
    Form
    -0.42
    RequestOptions
    -0.41
    form
    -0.41
    POSITIVE LOGITS
    saraba
    0.72
    Personendaten
    0.66
    ThemeOverlay
    0.66
     EconPapers
    0.64
    MigrationBuilder
    0.64
    #
    0.64
    TagMode
    0.63
    tonode
    0.63
    IndentedString
    0.63
    EndGlobalSection
    0.62
    Activations Density 0.001%

    No Known Activations