© 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. 0-CLT-HP
    7. 43349
    Prev
    Next
    INDEX
    Explanations

    iTunes

    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
     fighters
    -0.94
     Fighters
    -0.65
     Reverso
    -0.64
    olu
    -0.59
    AnchorStyles
    -0.59
     referenties
    -0.57
     CreateTagHelper
    -0.56
    EDEFAULT
    -0.56
     Leu
    -0.55
     Exactos
    -0.54
    POSITIVE LOGITS
     policiales
    0.52
     exécu
    0.51
     sociaux
    0.51
    ">—
    0.50
     }</
    0.49
    CloseOperation
    0.48
     béné
    0.47
    HostException
    0.47
     soprav
    0.47
    原始内容存档于
    0.47
    Activations Density 0.127%

    No Known Activations