© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91962
    Prev
    Next
    INDEX
    Explanations

    symbols

    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
     appeared
    -0.90
     apparent
    -0.85
    ″]
    -0.77
     appear
    -0.75
     appar
    -0.75
     ་་
    -0.75
     InputDecoration
    -0.73
     appearances
    -0.73
     appears
    -0.72
    apparent
    -0.72
    POSITIVE LOGITS
    $\
    0.58
     ,
    0.53
     and
    0.50
    evos
    0.49
     or
    0.48
    use
    0.47
    o
    0.47
    send
    0.47
     Con
    0.46
    k
    0.46
    Activations Density 1.701%

    No Known Activations