© 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. 1-CLT-HP
    7. 12140
    Prev
    Next
    INDEX
    Explanations

    Singapore

    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
    ContentAsync
    -0.65
    webElementXpaths
    -0.60
     GetEnumerator
    -0.59
    Tikang
    -0.59
    ChildScrollView
    -0.57
    +#+#
    -0.53
    AttributeSet
    -0.53
     consultato
    -0.52
     travailleurs
    -0.52
    AdapterView
    -0.50
    POSITIVE LOGITS
    RenderAtEndOf
    0.60
    astéroïdes
    0.58
    بوابة
    0.56
     incendi
    0.56
    kuuta
    0.55
     insurgency
    0.54
    hängt
    0.51
    urgency
    0.50
    iske
    0.50
    istice
    0.50
    Activations Density 0.011%

    No Known Activations