© 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. 0-CLT-HP
    7. 38929
    Prev
    Next
    INDEX
    Explanations

    bubble

    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
     bubbles
    -2.38
     bubble
    -2.25
    bubble
    -2.08
     Bubble
    -1.92
    bubbles
    -1.87
    Bubble
    -1.80
     Bubbles
    -1.77
     burbujas
    -1.50
     burbuja
    -1.44
    Bubbles
    -1.41
    POSITIVE LOGITS
     broken
    0.51
     nhiêu
    0.51
    terer
    0.49
    dav
    0.49
    tz
    0.48
    ,
    0.48
     bridge
    0.47
    nstein
    0.47
    ts
    0.46
     snippetHide
    0.45
    Activations Density 0.960%

    No Known Activations