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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1171
    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
    ServletConfig
    -0.48
     diritti
    -0.47
    sspiel
    -0.47
     sensor
    -0.47
    kwds
    -0.46
    WriteBarrier
    -0.44
     GS
    -0.44
    TargetException
    -0.44
    ENSIVE
    -0.44
     •
    -0.44
    POSITIVE LOGITS
    abrigo
    0.66
    onnaise
    0.55
     Berber
    0.52
     aprons
    0.52
    createCanvas
    0.52
     asiatique
    0.52
     Altura
    0.51
    ècie
    0.49
     maroca
    0.49
     StatefulWidget
    0.49
    Activations Density 0.003%

    No Known Activations