© 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. 4-CLT-HP
    7. 1909
    Prev
    Next
    INDEX
    Explanations

    code/software

    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>
    -1.62
     myſelf
    -0.85
     itſelf
    -0.85
     poffe
    -0.83
     fhew
    -0.82
     poffible
    -0.81
     uſed
    -0.80
     deſt
    -0.77
     diſt
    -0.76
     Efq
    -0.76
    POSITIVE LOGITS
     Newtonsoft
    0.35
    abestanden
    0.35
     otomatig
    0.34
    mación
    0.30
    
    0.30
     مشين
    0.30
     Else
    0.29
    oughed
    0.29
    TagHelpers
    0.29
     Transfers
    0.28
    Activations Density 1.368%

    No Known Activations