© 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. 94404
    Prev
    Next
    INDEX
    Explanations

    opol

    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
    nians
    -0.97
    neman
    -0.93
    tain
    -0.85
    opol
    -0.58
     nonatomic
    -0.57
    IAB
    -0.54
     saites
    -0.52
    OnAdd
    -0.52
    lorette
    -0.48
    rizona
    -0.47
    POSITIVE LOGITS
     információk
    0.56
    นะนำ
    0.53
    getDescriptor
    0.52
    JspWriter
    0.52
    berater
    0.52
     referenties
    0.51
     gué
    0.51
     kaarangay
    0.50
     graça
    0.50
    pielen
    0.49
    Activations Density 0.103%

    No Known Activations