© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1362
    Prev
    Next
    INDEX
    Explanations

    Instructions or locations

    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
    ie
    -0.70
    ner
    -0.63
    time
    -0.60
    ization
    -0.59
    n
    -0.58
    ier
    -0.56
     betweenstory
    -0.56
    r
    -0.56
    iem
    -0.54
    ik
    -0.54
    POSITIVE LOGITS
     Мексичка
    0.73
     consultato
    0.61
     vôtre
    0.61
     виправивши
    0.60
    HomeAsUpEnabled
    0.60
     AudioClip
    0.60
     scatola
    0.59
    олові
    0.58
    ècie
    0.57
    atillas
    0.57
    Activations Density 0.141%

    No Known Activations