© 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. 5-CLT-HP
    4. 96611
    Prev
    Next
    INDEX
    Explanations

    expressing thought/opinion

    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
    saraba
    -0.59
    igshid
    -0.57
     chaude
    -0.56
     nemlig
    -0.56
     longues
    -0.56
     and
    -0.54
    AddTagHelper
    -0.54
    AndEndTag
    -0.53
     blessé
    -0.53
     riconoscimento
    -0.53
    POSITIVE LOGITS
     المعيارى
    0.63
     Crot
    0.58
     vapormax
    0.56
    횟
    0.56
     препратки
    0.56
     tfsi
    0.55
     beſt
    0.55
     kazak
    0.54
    ialog
    0.53
    ()]);
    0.53
    Activations Density 0.002%

    No Known Activations