© 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. 94712
    Prev
    Next
    INDEX
    Explanations

    .

    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
    pyx
    -0.48
     pageContext
    -0.43
    Matching
    -0.42
    SWR
    -0.42
    NSError
    -0.41
     Messaging
    -0.41
    orky
    -0.41
    utación
    -0.40
    Хьажоргаш
    -0.40
     humming
    -0.40
    POSITIVE LOGITS
    SourceChecksum
    0.76
     CreateTagHelper
    0.62
    DeleteBehavior
    0.58
    Билгалдахарш
    0.57
    AndPassword
    0.57
    KURZBESCHREIBUNG
    0.56
     Infórmanos
    0.56
    afficheront
    0.56
    libft
    0.56
    InjectAttribute
    0.56
    Activations Density 0.023%

    No Known Activations