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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5660
    Prev
    Next
    INDEX
    Explanations

    Technical descriptions

    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
    Datuak
    -0.98
     '\\;'
    -0.90
     للمعارف
    -0.88
    rrggbb
    -0.86
     الحره
    -0.85
    الإنجليزية
    -0.84
     StatelessWidget
    -0.83
     onOptions
    -0.82
    aarrggbb
    -0.81
     CreateTagHelper
    -0.81
    POSITIVE LOGITS
    ,
    0.49
    M
    0.43
    it
    0.42
     mà
    0.42
    Sm
    0.41
    Ch
    0.41
    O
    0.40
    w
    0.40
    S
    0.40
    be
    0.39
    Activations Density 0.033%

    No Known Activations