© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3452
    Prev
    Next
    INDEX
    Explanations

    scientific/technical limitations

    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
     limited
    -1.10
    limited
    -1.01
    Limited
    -0.93
     Limited
    -0.92
     limiting
    -0.91
     limitations
    -0.89
     terbatas
    -0.87
     limitado
    -0.84
     limitation
    -0.84
     limit
    -0.80
    POSITIVE LOGITS
     betweenstory
    0.90
    ItemBackground
    0.68
     Wikimedijinoj
    0.60
    出版年
    0.60
    ьаж
    0.58
    ContentAlignment
    0.56
    Gweler
    0.56
     مشين
    0.55
    istoitu
    0.54
    SharedCtor
    0.54
    Activations Density 0.014%

    No Known Activations