© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2853
    Prev
    Next
    INDEX
    Explanations

    places

    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
    <bos>
    -0.56
    fon
    -0.49
     JAXB
    -0.48
     Video
    -0.47
    rol
    -0.47
    zzleHttp
    -0.47
    ivir
    -0.46
    mes
    -0.46
    lp
    -0.45
    Singing
    -0.45
    POSITIVE LOGITS
     OMITBAD
    0.69
     NSCoder
    0.66
    reportWebVitals
    0.64
    GeneratedMessage
    0.57
    ----</
    0.56
     TextAppearance
    0.56
     Familienname
    0.54
    Бахар
    0.53
     horaire
    0.53
    GraphicsUnit
    0.52
    Activations Density 0.028%

    No Known Activations