© 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. 20-CLT-HP
    7. 75148
    Prev
    Next
    INDEX
    Explanations

    Technical/proper names

    np_max-act-logits · 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
    ]--;
    -0.68
    tagext
    -0.65
     محفوظة
    -0.63
     متعلقه
    -0.61
     ujednoznacz
    -0.60
    AndroidJUnit
    -0.58
    adaptiveStyles
    -0.56
    neté
    -0.55
    oa̍t
    -0.54
    رشف
    -0.54
    POSITIVE LOGITS
     énergé
    0.59
     prêts
    0.55
     étend
    0.55
     convaincre
    0.54
     épar
    0.51
     arrière
    0.50
    iste
    0.49
     définiti
    0.49
     médicaux
    0.48
     scolaires
    0.48
    Activations Density 0.000%

    No Known Activations