© 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. 4-CLT-HP
    7. 3408
    Prev
    Next
    INDEX
    Explanations

    Formal documents and communication

    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
    ροι
    -0.50
     sumpay
    -0.49
     ag
    -0.46
     under
    -0.45
     ar
    -0.45
    MathML
    -0.45
     bó
    -0.44
     Tokyo
    -0.43
     sum
    -0.43
     certain
    -0.41
    POSITIVE LOGITS
    Portály
    0.75
    KommentareTeilen
    0.60
    ValueStyle
    0.60
    InputBorder
    0.59
     bezeichneter
    0.57
    ➟
    0.55
     Superhost
    0.53
    Демографія
    0.53
    ագրություններ
    0.52
     étend
    0.51
    Activations Density 0.003%

    No Known Activations