© 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. 5876
    Prev
    Next
    INDEX
    Explanations

    physics

    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
     soeur
    -0.59
    zyb
    -0.59
     Jurí
    -0.59
     effray
    -0.57
     navires
    -0.56
     pouvoirs
    -0.55
     définiti
    -0.55
     AssemblyTitle
    -0.55
     brancas
    -0.54
    bol
    -0.54
    POSITIVE LOGITS
     ويكيميديا
    0.56
    SuppressLint
    0.56
    "]);
    0.56
    ParallelGroup
    0.54
    GEBURTSDATUM
    0.52
     effect
    0.52
    ]),
    0.51
    endpush
    0.50
    ----</
    0.49
     Réponses
    0.49
    Activations Density 0.003%

    No Known Activations