© 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. 195
    Prev
    Next
    INDEX
    Explanations

    articles

    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
     tartalomajánló
    -0.79
    aarrggbb
    -0.78
     beginnetje
    -0.77
     myſelf
    -0.77
     kaynağından
    -0.73
     <=",
    -0.73
    WithIOException
    -0.72
     виправивши
    -0.72
    UnusedPrivate
    -0.71
    verwijspagina
    -0.67
    POSITIVE LOGITS
     reason
    0.48
     choice
    0.48
     designation
    0.47
     so
    0.45
     frequent
    0.45
     massive
    0.44
     willingness
    0.42
     increased
    0.41
     availability
    0.41
     perché
    0.41
    Activations Density 0.003%

    No Known Activations