© 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. 1-CLT-HP
    7. 10493
    Prev
    Next
    INDEX
    Explanations

    hir

    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
    hir
    -1.34
     Roskov
    -0.83
     مواليد
    -0.82
    lamydia
    -0.79
    Autoritní
    -0.76
    SourceChecksum
    -0.71
    HIR
    -0.70
    DockStyle
    -0.70
    Filmografia
    -0.70
     censiti
    -0.68
    POSITIVE LOGITS
     ray
    0.49
    red
    0.46
    ए
    0.44
     red
    0.44
    che
    0.43
    ر
    0.43
    க்க
    0.42
    reda
    0.42
    aras
    0.41
    Waar
    0.41
    Activations Density 0.048%

    No Known Activations