© 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. 4-CLT-HP
    7. 654
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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
     referenties
    -0.90
    UserScript
    -0.79
     Vikipedi
    -0.76
    $}}
    -0.69
    featureID
    -0.69
     &___
    -0.68
    contentLoaded
    -0.68
     createSprite
    -0.67
    :")
    -0.67
    parsedMessage
    -0.67
    POSITIVE LOGITS
     obsah
    0.46
     if
    0.44
    <bos>
    0.44
     traités
    0.42
     ако
    0.42
     sanitaires
    0.41
    ViewFeatures
    0.41
    Sklici
    0.40
     якщо
    0.40
     indien
    0.40
    Activations Density 0.007%

    No Known Activations