© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4374
    Prev
    Next
    INDEX
    Explanations

    yn

    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
    Geplaatst
    -0.69
     surla
    -0.64
     MainAxisSize
    -0.64
    !*\
    -0.61
    avadoc
    -0.61
    IntoConstraints
    -0.60
     AssemblyCulture
    -0.60
     betweenstory
    -0.60
    存于互联网档案馆
    -0.59
    createServer
    -0.59
    POSITIVE LOGITS
    Al
    0.59
    al
    0.54
    OLDS
    0.50
    InstanceState
    0.49
    U
    0.49
     υ
    0.47
    Li
    0.47
    LD
    0.47
    ld
    0.47
    lds
    0.46
    Activations Density 0.016%

    No Known Activations