Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44426
    Prev
    Next
    INDEX
    Explanations

    Scientific/medical texts

    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
    NUMX
    -0.89
    WriteBarrier
    -0.89
    GEBURTS
    -0.84
     CURIAM
    -0.82
    
    -0.81
    ^(@)
    -0.80
    ंदीखरीदारी
    -0.79
     endwhile
    -0.77
    parsedMessage
    -0.77
    windowFixed
    -0.76
    POSITIVE LOGITS
     to
    0.59
     or
    0.50
     (
    0.48
     for
    0.48
     at
    0.47
     so
    0.47
     and
    0.47
     
    0.46
     on
    0.46
    ted
    0.46
    Activations Density 0.049%

    No Known Activations