© 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. 91535
    Prev
    Next
    INDEX
    Explanations

    user interaction

    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
    twimg
    -0.52
    存于互联网档案馆
    -0.52
    tawan
    -0.50
    apse
    -0.48
    IsContent
    -0.47
    有一
    -0.47
     Wert
    -0.47
     Apro
    -0.47
     participated
    -0.46
    arted
    -0.46
    POSITIVE LOGITS
     can
    0.98
     kunnen
    0.66
     dapat
    0.65
    can
    0.64
    rungsseite
    0.61
     können
    0.60
    protoimpl
    0.60
    IUrlHelper
    0.59
    homonymie
    0.59
     pouvez
    0.58
    Activations Density 0.004%

    No Known Activations