© 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. 0-CLT-HP
    7. 93308
    Prev
    Next
    INDEX
    Explanations

    Scientific and geographical terms

    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
     Sharpe
    -0.74
    ulina
    -0.64
     Hone
    -0.63
    hausen
    -0.63
    vill
    -0.62
    ness
    -0.62
    rette
    -0.59
    sy
    -0.56
    burne
    -0.56
    олові
    -0.56
    POSITIVE LOGITS
     للمعارف
    0.77
    enumii
    0.72
     Infórmanos
    0.66
    ftagPool
    0.61
    AddHtmlAttribute
    0.60
    EReference
    0.60
     ProtoMessage
    0.59
    Geplaatst
    0.58
     Италијани
    0.56
    adaptiveStyles
    0.55
    Activations Density 0.141%

    No Known Activations