© 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. 1-CLT-HP
    7. 14350
    Prev
    Next
    INDEX
    Explanations

    lop

    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
    lops
    -1.23
    lop
    -0.99
    ISupport
    -0.53
    ian
    -0.52
     nakalista
    -0.52
    ial
    -0.52
    LOP
    -0.51
    ien
    -0.51
     للمعارف
    -0.48
    la
    -0.48
    POSITIVE LOGITS
     NUKAT
    0.68
    verwijspagina
    0.66
    исленность
    0.63
    EndContext
    0.60
    
    0.58
    perfectly
    0.57
    scriptId
    0.57
    setBold
    0.55
    aryana
    0.55
     Perfectly
    0.55
    Activations Density 0.026%

    No Known Activations