© 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. 5-CLT-HP
    7. 5828
    Prev
    Next
    INDEX
    Explanations

    jquery

    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
    +#+#
    -0.65
    ніципалі
    -0.61
    atalos
    -0.58
     للمعارف
    -0.57
     تانيه
    -0.57
     otomatig
    -0.56
    ItemBackground
    -0.53
    ramienta
    -0.52
    yarnpkg
    -0.51
     odkazy
    -0.49
    POSITIVE LOGITS
    Coordonnées
    0.60
    ratulations
    0.59
     role
    0.58
    Bibliograf
    0.56
     experiments
    0.55
     problem
    0.54
     experimentation
    0.54
     brain
    0.54
     joke
    0.52
     debating
    0.52
    Activations Density 0.000%

    No Known Activations