© 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. 1-CLT-HP
    7. 14642
    Prev
    Next
    INDEX
    Explanations

    straightening

    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
    rungsseite
    -0.64
     Numerade
    -0.62
     estekak
    -0.61
    SequentialGroup
    -0.61
     initComponents
    -0.57
     للمعارف
    -0.56
    ///</
    -0.56
    |}{$
    -0.56
     utafiti
    -0.54
    idł
    -0.53
    POSITIVE LOGITS
     Paglinawan
    0.74
     your
    0.65
     yourself
    0.58
    HasForeignKey
    0.55
     chiếu
    0.55
    HomeAsUpEnabled
    0.54
     ourselves
    0.51
     through
    0.50
    下载附件
    0.49
    issau
    0.49
    Activations Density 0.010%

    No Known Activations