© 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. 91436
    Prev
    Next
    INDEX
    Explanations

    programming/software development

    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
     Савезне
    -0.69
     المعيارى
    -0.67
     AssemblyCulture
    -0.65
    ilarities
    -0.64
    Formation
    -0.63
     الوطنيه
    -0.62
    glGen
    -0.60
    ällor
    -0.60
    simov
    -0.59
     autorisés
    -0.59
    POSITIVE LOGITS
    /***/
    0.43
    Heidi
    0.39
    SourceChecksum
    0.39
    Бележки
    0.39
     closely
    0.39
     Москву
    0.39
    ExtendWith
    0.39
    especie
    0.39
     jezik
    0.39
    ]))
    0.38
    Activations Density 0.034%

    No Known Activations