© 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. 5924
    Prev
    Next
    INDEX
    Explanations

    relationships and analysis

    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
    olum
    -0.60
    windowFixed
    -0.60
    USAL
    -0.60
    annica
    -0.59
    MLLoader
    -0.58
    WebElementEntity
    -0.57
    lunda
    -0.57
     akka
    -0.56
    utang
    -0.55
     hinaus
    -0.54
    POSITIVE LOGITS
    IOP
    0.50
    Биография
    0.49
    IOD
    0.47
    io
    0.46
    iod
    0.45
    يور
    0.45
    يميديا
    0.43
    rungsseite
    0.43
     DPD
    0.42
    Hozzáférés
    0.42
    Activations Density 0.002%

    No Known Activations