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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90464
    Prev
    Next
    INDEX
    Explanations

    breakaway

    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
     Paglinawan
    -0.59
    MigrationBuilder
    -0.55
    __':
    -0.54
    "?>
    -0.50
     opérateur
    -0.50
    cloudfront
    -0.48
    anyahu
    -0.47
     Sabha
    -0.46
    elho
    -0.45
     ]}
    -0.44
    POSITIVE LOGITS
     ſmall
    0.77
     Theſe
    0.76
     uſed
    0.69
     CreateTagHelper
    0.68
     itſelf
    0.68
     cauſe
    0.67
     uſe
    0.66
     ſtand
    0.64
     caufe
    0.63
     ſtill
    0.63
    Activations Density 1.113%

    No Known Activations