© 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. 11535
    Prev
    Next
    INDEX
    Explanations

    rani

    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
    rani
    -3.02
    rana
    -0.79
    ranie
    -0.66
    rane
    -0.61
    rano
    -0.59
    lani
    -0.58
    rania
    -0.57
    TagMode
    -0.52
    jois
    -0.50
    RegistryLite
    -0.47
    POSITIVE LOGITS
     مرئيه
    0.76
    AndEndTag
    0.73
     Theſe
    0.66
    expandindo
    0.66
     cherchés
    0.64
    PerformLayout
    0.64
     réguli
    0.63
     sanitaires
    0.62
    IsPostBack
    0.62
    rungsseite
    0.59
    Activations Density 0.010%

    No Known Activations