© 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. 93340
    Prev
    Next
    INDEX
    Explanations

    act

    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
     Act
    -2.25
    Act
    -1.76
     act
    -1.34
     ACT
    -1.05
    act
    -1.00
     Acts
    -0.89
    GEBURTSDATUM
    -0.83
    SequentialGroup
    -0.79
    buttonBar
    -0.78
    CppMethod
    -0.77
    POSITIVE LOGITS
     Monfieur
    0.67
     aveug
    0.60
     ainfi
    0.57
     Egli
    0.57
     tué
    0.57
     Moderato
    0.56
     avoient
    0.55
    ation
    0.54
     négatif
    0.54
    ures
    0.54
    Activations Density 0.006%

    No Known Activations