© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3381
    Prev
    Next
    INDEX
    Explanations

    finger

    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
     invokingState
    -0.50
    rcParams
    -0.47
     True
    -0.47
    łku
    -0.47
    出版年
    -0.47
    owohl
    -0.44
     sadar
    -0.43
     дописавши
    -0.42
    utnik
    -0.42
     Malo
    -0.42
    POSITIVE LOGITS
     snippetHide
    0.84
     تضيفلها
    0.73
     MenuView
    0.65
     Administrativna
    0.63
    apnews
    0.59
    makeConstraints
    0.59
    WireFormatLite
    0.59
     Paglinawan
    0.57
    CPtr
    0.57
     distanciation
    0.56
    Activations Density 0.001%

    No Known Activations