© 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. 5-CLT-HP
    7. 96739
    Prev
    Next
    INDEX
    Explanations

    from by

    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
    期刊论文
    -0.62
    <bos>
    -0.60
    twimg
    -0.59
     Мексичка
    -0.57
    NewUrlParser
    -0.54
    UVWXYZ
    -0.52
    SuppressLint
    -0.51
    \|_{
    -0.50
    wale
    -0.49
    ubuntu
    -0.47
    POSITIVE LOGITS
    出版年
    0.85
    Personendaten
    0.69
     صوتيه
    0.63
     subjecting
    0.60
     forcing
    0.59
     flesta
    0.58
     diferite
    0.58
    Any
    0.57
     taking
    0.57
    any
    0.57
    Activations Density 0.014%

    No Known Activations