© 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. 0-CLT-HP
    7. 92452
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    DockStyle
    -0.76
     nonUne
    -0.64
    LEncoder
    -0.59
    μως
    -0.58
     aéreo
    -0.57
    ELTS
    -0.55
    Zeneca
    -0.54
    XtraEditors
    -0.54
    Literatuur
    -0.53
    اديم
    -0.52
    POSITIVE LOGITS
    gnore
    0.53
    固
    0.48
    ed
    0.48
    ess
    0.47
    化
    0.47
    Collegamenti
    0.46
    坐
    0.46
    es
    0.46
    toma
    0.45
    Twig
    0.44
    Activations Density 1.032%

    No Known Activations