© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14420
    Prev
    Next
    INDEX
    Explanations

    Programming

    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
     
    -1.15
    ↵
    -1.04
    .
    -0.94
    ,
    -0.94
      
    -0.90
    1
    -0.79
     (
    -0.79
    <strong>
    -0.78
     and
    -0.72
    (
    -0.72
    POSITIVE LOGITS
    parsedMessage
    1.73
     myſelf
    1.68
     autorytatywna
    1.67
     Мексичка
    1.55
    SharedDtor
    1.53
     Efq
    1.52
    __':
    1.51
     invokingState
    1.49
     ―――――
    1.49
     itſelf
    1.48
    Activations Density 0.456%

    No Known Activations