© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45369
    Prev
    Next
    INDEX
    Explanations

    Document excerpts

    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
    tagHelperRunner
    -0.54
    وأضاف
    -0.52
     GenerationType
    -0.51
    arnes
    -0.51
    MLLoader
    -0.50
    nī
    -0.50
    ノロ
    -0.49
    AutoScaleMode
    -0.49
    beforeEach
    -0.48
    rigley
    -0.48
    POSITIVE LOGITS
     متعلقه
    0.71
    QMetaType
    0.64
    VersionUID
    0.63
    ymce
    0.59
     ***!
    0.55
     billet
    0.53
    vues
    0.52
     RemoteException
    0.52
    Viel
    0.51
    atrième
    0.51
    Activations Density 1.915%

    No Known Activations