© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10582
    Prev
    Next
    INDEX
    Explanations

    μ

    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
     Bihar
    -0.44
    .
    -0.42
     Klassi
    -0.42
     Cortez
    -0.41
    beni
    -0.40
     shat
    -0.40
     highly
    -0.40
    .__
    -0.40
    acia
    -0.40
     inherit
    -0.40
    POSITIVE LOGITS
     automatiques
    0.91
     rempliss
    0.91
     supérieures
    0.87
     définiti
    0.85
     énergé
    0.82
     supérieurs
    0.82
     avoient
    0.82
     quelcon
    0.82
     oreilles
    0.81
     écout
    0.81
    Activations Density 0.014%

    No Known Activations