© 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. 43389
    Prev
    Next
    INDEX
    Explanations

    unless

    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
     unless
    -1.77
    unless
    -1.58
     Unless
    -1.50
    Unless
    -1.47
     finger
    -1.09
    除非
    -0.92
     Finger
    -0.90
    finger
    -0.89
    Finger
    -0.86
     vectorielles
    -0.66
    POSITIVE LOGITS
    IMPORTED
    0.63
     there
    0.60
    TestingModule
    0.60
    CloseOperation
    0.60
     ProtoMessage
    0.59
     you
    0.57
    SequentialGroup
    0.56
     Indeed
    0.55
     اطلع
    0.55
    lapsingToolbar
    0.55
    Activations Density 0.992%

    No Known Activations