© 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. 20-CLT-HP
    7. 72504
    Prev
    Next
    INDEX
    Explanations

    HTML tables

    np_max-act-logits · 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
     חיצוניים
    -0.68
     ivelany
    -0.63
    Soorten
    -0.56
     panoramique
    -0.54
     régionale
    -0.54
     lavorato
    -0.54
    曖昧さ回避
    -0.54
     marins
    -0.54
     Exactos
    -0.54
    wants
    -0.54
    POSITIVE LOGITS
     don
    0.86
     pose
    0.61
     do
    0.59
     experience
    0.57
     cause
    0.56
    don
    0.54
     kaynağından
    0.53
     Don
    0.52
    brtc
    0.51
    Don
    0.49
    Activations Density 0.002%

    No Known Activations