© 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. 15220
    Prev
    Next
    INDEX
    Explanations

    rant

    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
     Vikipedi
    -0.68
    oporosis
    -0.66
    ValueStyle
    -0.59
    tiss
    -0.59
    RegressionTest
    -0.57
    webElementXpaths
    -0.57
    PRD
    -0.56
    textAppearance
    -0.55
    complexType
    -0.54
    enterOuterAlt
    -0.53
    POSITIVE LOGITS
    Cyfeiriadau
    0.63
     founders
    0.50
     xanth
    0.49
    esModule
    0.48
     sache
    0.46
    
    0.46
     founder
    0.46
    žen
    0.46
    ọi
    0.46
     〈
    0.45
    Activations Density 0.025%

    No Known Activations