© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3470
    Prev
    Next
    INDEX
    Explanations

    rather

    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
    ագրություններ
    -1.02
    tvguidetime
    -0.90
    webElementXpaths
    -0.86
    HostException
    -0.85
     المعيارى
    -0.81
    GEBURTSDATUM
    -0.79
    WriteTagHelper
    -0.77
    piram
    -0.75
    tonode
    -0.73
     '\\;'
    -0.73
    POSITIVE LOGITS
    though
    0.44
     بيها
    0.43
     noDo
    0.42
     while
    0.41
     despite
    0.40
     Unterschied
    0.40
     if
    0.40
     unless
    0.39
    tudo
    0.39
     although
    0.39
    Activations Density 0.018%

    No Known Activations