© 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. 94587
    Prev
    Next
    INDEX
    Explanations

    Fragmented text

    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
     Roskov
    -0.77
     Celle
    -0.59
    AndEndTag
    -0.59
     منها
    -0.59
    CopyWith
    -0.58
     invokingState
    -0.58
    brandt
    -0.58
    ransition
    -0.57
     Мексичка
    -0.57
    Tipo
    -0.56
    POSITIVE LOGITS
     חיצוניים
    0.50
     المعيارى
    0.47
     صوتيه
    0.46
    @{
    0.44
     分页
    0.41
     bu
    0.40
    hoga
    0.39
     esternos
    0.39
     correctes
    0.39
     conjunta
    0.39
    Activations Density 0.000%

    No Known Activations