© 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. 5-CLT-HP
    7. 92614
    Prev
    Next
    INDEX
    Explanations

    def

    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
    <bos>
    -0.69
     &___
    -0.63
     fernández
    -0.61
     lópez
    -0.58
     hyö
    -0.57
     rodríguez
    -0.56
     saites
    -0.55
    มาะ
    -0.54
     juſ
    -0.54
    PostMapping
    -0.53
    POSITIVE LOGITS
    ]--;
    0.54
     disambiguazione
    0.50
    openConnection
    0.47
     fibrillation
    0.46
    atchewan
    0.45
    printLine
    0.44
    himovic
    0.44
    pensione
    0.44
    cookieParser
    0.43
    gameserver
    0.43
    Activations Density 0.000%

    No Known Activations