© 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. 94274
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     []:
    -0.55
    entrion
    -0.43
     bukanlah
    -0.41
    Gret
    -0.41
    .~(\
    -0.39
    ≫
    -0.39
    forRoot
    -0.39
    étr
    -0.39
    Rtl
    -0.38
     lẻ
    -0.38
    POSITIVE LOGITS
     تضيفلها
    0.85
    Билгалдахарш
    0.77
    cyklopedia
    0.75
    MessageOf
    0.75
    WithIOException
    0.72
    ModelAdmin
    0.70
    tagHelperRunner
    0.69
    AndEndTag
    0.69
    UnusedPrivate
    0.69
     Meksiku
    0.69
    Activations Density 0.001%

    No Known Activations