© 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. 0-CLT-HP
    7. 42009
    Prev
    Next
    INDEX
    Explanations

    **

    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
     *
    -1.91
     **
    -1.83
    **
    -1.59
     (*
    -1.58
     ***
    -1.52
     *,
    -1.41
    )*
    -1.38
    (*
    -1.37
    **.
    -1.33
    =*
    -1.31
    POSITIVE LOGITS
     مشين
    0.88
    tagHelperRunner
    0.81
    QMetaType
    0.81
    AutoresizingMask
    0.79
    IUrlHelper
    0.79
    ########.
    0.79
    setVerticalGroup
    0.77
     pinulongan
    0.76
     poffible
    0.75
     ſhe
    0.75
    Activations Density 0.800%

    No Known Activations