© 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. 4-CLT-HP
    7. 4618
    Prev
    Next
    INDEX
    Explanations

    of

    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
     majesty
    -0.60
    twimg
    -0.59
     grandeur
    -0.58
     charm
    -0.58
     الحره
    -0.57
     cura
    -0.57
     splendour
    -0.57
     excite
    -0.56
     charisma
    -0.56
     begeistert
    -0.56
    POSITIVE LOGITS
    PreferredItem
    0.59
    Rujuakan
    0.58
    addCriterion
    0.49
    Spoljašnje
    0.48
    ⟬
    0.48
     fall
    0.46
     Numerade
    0.46
    /−
    0.46
    udder
    0.46
     TextAppearance
    0.45
    Activations Density 0.004%

    No Known Activations