© 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. 4-CLT-HP
    7. 264
    Prev
    Next
    INDEX
    Explanations

    Location

    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
     somewhere
    -0.86
     MenuView
    -0.77
    somewhere
    -0.65
    Somewhere
    -0.63
     Somewhere
    -0.62
     someplace
    -0.62
     something
    -0.59
     betweenstory
    -0.54
     nahilalakip
    -0.53
    PreferredItem
    -0.52
    POSITIVE LOGITS
     arrière
    0.62
    baguna
    0.61
    intera
    0.58
     semula
    0.58
     vzh
    0.56
     vectoriales
    0.56
     gloire
    0.55
     besök
    0.55
     espalda
    0.54
     préfé
    0.54
    Activations Density 0.013%

    No Known Activations