© 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. 4817
    Prev
    Next
    INDEX
    Explanations

    Technical documents

    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
    ⓧ
    -0.62
    Personendaten
    -0.59
     offline
    -0.55
    ніципалі
    -0.53
     plonge
    -0.51
    kleid
    -0.50
    Dated
    -0.50
     Herod
    -0.49
    commune
    -0.49
    uffy
    -0.49
    POSITIVE LOGITS
    )_/¯
    0.79
     دیکھیے
    0.63
    AndroidJUnit
    0.61
     noDo
    0.60
     سكانية
    0.59
     viewDidLoad
    0.56
     createSprite
    0.53
    openConnection
    0.52
    makeText
    0.52
    AndEndTag
    0.51
    Activations Density 0.003%

    No Known Activations