© 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. 4-CLT-HP
    7. 929
    Prev
    Next
    INDEX
    Explanations

    of

    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
    TintMode
    -0.70
    HasForeignKey
    -0.51
    DotNetBar
    -0.50
    躇
    -0.49
    mido
    -0.47
    ică
    -0.45
     useDispatch
    -0.45
     című
    -0.44
    OUNT
    -0.44
     vermelhas
    -0.44
    POSITIVE LOGITS
    richTextPanel
    0.65
     Normdatei
    0.60
     Aristi
    0.60
    fjspx
    0.59
    SequentialGroup
    0.55
    mmä
    0.54
    lccn
    0.54
    basicConfig
    0.53
     seorang
    0.53
     suivante
    0.52
    Activations Density 0.007%

    No Known Activations