© 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. 20-CLT-HP
    7. 71839
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · 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
     propOrder
    -1.34
     resourceCulture
    -1.20
    DockStyle
    -1.06
     Meksiku
    -0.98
    RegistryLite
    -0.97
    XmlAccessorType
    -0.97
     Efq
    -0.95
    tagext
    -0.95
     Jefus
    -0.94
     sauvages
    -0.92
    POSITIVE LOGITS
    .
    0.58
    <eos>
    0.52
    ↵↵
    0.51
     for
    0.48
    ↵
    0.46
    ​
    0.46
     one
    0.45
     like
    0.41
    ...
    0.41
    -
    0.40
    Activations Density 0.000%

    No Known Activations