© 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. 0-CLT-HP
    7. 94659
    Prev
    Next
    INDEX
    Explanations

    Code/technical language

    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
    FS
    -1.40
    fs
    -1.33
     FS
    -0.66
    rs
    -0.57
    s
    -0.55
    Fs
    -0.54
     fs
    -0.51
     Thinking
    -0.51
    ings
    -0.48
    map
    -0.47
    POSITIVE LOGITS
    StoryboardSegue
    1.12
    XmlAccessType
    0.98
    IUrlHelper
    0.87
    HtmlAttribute
    0.86
     فريبيس
    0.86
     JpaRepository
    0.84
    contentLoaded
    0.84
    UnknownFields
    0.83
     Normdatei
    0.83
    makeConstraints
    0.82
    Activations Density 0.082%

    No Known Activations