© 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. 97485
    Prev
    Next
    INDEX
    Explanations

    low

    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
     EconPapers
    -1.02
    TypedDataSet
    -0.95
     فريبيس
    -0.94
     kaarangay
    -0.92
     autorytatywna
    -0.91
    ArrowToggle
    -0.91
    AsUp
    -0.91
     >=",
    -0.91
     ddelweddau
    -0.91
    aarrggbb
    -0.90
    POSITIVE LOGITS
     \
    0.36
    Speed
    0.35
     no
    0.35
    <
    0.33
    leid
    0.32
     
    0.32
     h
    0.31
     t
    0.31
     speed
    0.31
     временем
    0.31
    Activations Density 0.139%

    No Known Activations