© 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. 91418
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    principalColumn
    -0.31
    icoot
    -0.29
     popolari
    -0.28
     stöd
    -0.28
     renfor
    -0.28
    tics
    -0.28
     diventare
    -0.27
     aanbod
    -0.27
     gaun
    -0.27
     brancas
    -0.27
    POSITIVE LOGITS
    AndEndTag
    0.78
    __*/
    0.77
     PRESENTATION
    0.73
    __(/*!
    0.72
     Wikispecies
    0.71
     ExecuteAsync
    0.69
     lenker
    0.68
     WebDriverWait
    0.66
    XmlAccessType
    0.66
     Krish
    0.66
    Activations Density 0.007%

    No Known Activations