© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95257
    Prev
    Next
    INDEX
    Explanations

    computer files directories

    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
    Spoljašnje
    -0.57
    =$?
    -0.53
    homonymie
    -0.53
    änning
    -0.49
    ftance
    -0.49
    Географи
    -0.49
     pů
    -0.48
     AspNetCore
    -0.47
    entyfik
    -0.47
    httphttps
    -0.46
    POSITIVE LOGITS
    GEBURTSDATUM
    0.69
     AssemblyCulture
    0.57
     المعيارى
    0.54
    laştır
    0.52
     Virol
    0.51
    ValueStyle
    0.51
     Hiv
    0.50
    ंदीखरीदारी
    0.50
     Examiner
    0.49
    ModelAdmin
    0.49
    Activations Density 0.004%

    No Known Activations