© 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. 1-CLT-HP
    7. 45947
    Prev
    Next
    INDEX
    Explanations

    Scientific and uncommon words

    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
    omor
    -0.96
    omorph
    -0.75
     consultato
    -0.68
    ValueStyle
    -0.64
    ьаж
    -0.60
    ysteme
    -0.56
     Administrativna
    -0.56
     NSCoder
    -0.54
    LogFactory
    -0.53
     Burton
    -0.51
    POSITIVE LOGITS
    protoimpl
    0.56
     تضيفلها
    0.52
    able
    0.52
    IBOutlet
    0.50
    ous
    0.49
    RectangleBorder
    0.48
    richtungen
    0.47
    Hauptartikel
    0.46
     समीक्षाएं
    0.45
     branch
    0.45
    Activations Density 0.029%

    No Known Activations