© 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. 94995
    Prev
    Next
    INDEX
    Explanations

    source

    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
     GetEnumerator
    -0.64
     teneb
    -0.60
    vių
    -0.55
     Cyclops
    -0.55
    KeySpec
    -0.54
    odeon
    -0.53
    يكب
    -0.52
    kasse
    -0.50
    нциклопе
    -0.49
    -------------</
    -0.49
    POSITIVE LOGITS
     خارجية
    0.64
    AddTagHelper
    0.63
    rungsseite
    0.52
     Watch
    0.49
    cury
    0.49
     jScrollPane
    0.48
    Watch
    0.48
     clinch
    0.47
    ::$_
    0.47
     sift
    0.47
    Activations Density 0.008%

    No Known Activations